Skip to content

ICCV 2025 — oral-paper writing studies

Read the argument, not only the topic

This inventory preserves the official presentation identity, inspected source revision and reading status. Each available study examines framing, organization, visual explanation, comparison conditions, supporting material and wording. Downloading a PDF does not count as reading it.

Use the contribution-specific plans for a short drafting route, the atlas for measured distributions, or an individual study for its exact source pinpoints. A writing study is not a scientific replication.

64 official oral records

64 source-inspected writing studies

0 selected scientific additions

Showing 64 of 64 papers.

001 · ICCV 2025 oral · Writing-focused manuscript scan + selected visuals inspected

GT-Loc: Unifying When and Where in Images Through a Joint Embedding Space

David G. Shatwell, Ishan Rajendrakumar Dave, Sirnam Swetha, Mubarak Shah

Writing lesson: Pair every input contract with a matched baseline and explain cyclic variables using one small worked distance example.

Scientific selection: Included for writing analysis only. Included in the complete official ICCV 2025 oral writing inventory. Scientific catalog membership and any promotion require separate review; this writing scan makes no promotion decision.

002 · ICCV 2025 oral · Writing-focused manuscript scan + selected visuals inspected

Scaling Laws for Native Multimodal Models

Mustafa Shukor, Enrico Fini, Victor Guilherme Turrisi da Costa, Matthieu Cord, Joshua Susskind, Alaaeldin El-Nouby

Writing lesson: Define the resource contract before presenting scaling curves, then include a downstream check and an explicit extrapolation boundary.

Scientific selection: Included for writing analysis only. Included in the complete official ICCV 2025 oral writing inventory. Scientific catalog membership and any promotion require separate review; this writing scan makes no promotion decision.

003 · ICCV 2025 oral · Writing-focused manuscript scan + selected visuals inspected

FixTalk: Taming Identity Leakage for High-Quality Talking Head Generation in Extreme Cases

Shuai Tan, Bill Gong, Bin Ji, Ye Pan

Writing lesson: Let a controlled failure diagnosis explain why each new module exists, and visually separate inherited, training-only and inference-time computation.

Scientific selection: Included for writing analysis only. Included in the complete official ICCV 2025 oral writing inventory. Scientific catalog membership and any promotion require separate review; this writing scan makes no promotion decision.

004 · ICCV 2025 oral · Writing-focused manuscript scan + selected visuals inspected

Differentiable Room Acoustic Rendering with Multi-View Vision Priors

Derong Jin, Ruohan Gao

Writing lesson: Make measured, rendered and approximated quantities distinct; repeat units and acquisition budgets next to every cross-scene comparison.

Scientific selection: Included for writing analysis only. Included in the complete official ICCV 2025 oral writing inventory. Scientific catalog membership and any promotion require separate review; this writing scan makes no promotion decision.

005 · ICCV 2025 oral · Writing-focused manuscript scan + selected visuals inspected

Token Activation Map to Visually Explain Multimodal LLMs

Yi Li, Hualiang Wang, Xinpeng Ding, Haonan Wang, Xiaomeng Li

Writing lesson: Define what an explanation metric measures before claiming improvement; align a method overview with its equations and preserve signed non-improvements.

Scientific selection: Included for writing analysis only. Included in the complete official ICCV 2025 oral writing inventory. Scientific catalog membership and any promotion require separate review; this writing scan makes no promotion decision.

006 · ICCV 2025 oral · Writing-focused manuscript scan + selected visuals inspected

Multi-View 3D Point Tracking

Frano Rajič, Haofei Xu, Marko Mihajlovic, Siyuan Li, Irem Demir, Emircan Gündoğdu, Lei Ke, Sergey Prokudin, Marc Pollefeys, Siyu Tang

Writing lesson: Place input privileges and baseline adaptations directly in captions, and distinguish sensor depth, estimated depth and optimization-derived depth.

Scientific selection: Included for writing analysis only. Included in the complete official ICCV 2025 oral writing inventory. Scientific catalog membership and any promotion require separate review; this writing scan makes no promotion decision.

007 · ICCV 2025 oral · Writing-focused manuscript scan + selected visuals inspected

Uncalibrated Structure from Motion on a Sphere

Jonathan Ventura, Viktor Larsson, Fredrik Kahl

Writing lesson: Keep theorem assumptions visible while explaining where the practical pipeline relaxes them, and name pseudo-ground truth as such.

Scientific selection: Included for writing analysis only. Included in the complete official ICCV 2025 oral writing inventory. Scientific catalog membership and any promotion require separate review; this writing scan makes no promotion decision.

008 · ICCV 2025 oral · Writing-focused manuscript scan + selected visuals inspected

Removing Cost Volumes from Optical Flow Estimators

Simon Kiefhaber, Stefan Roth, Simone Schaub-Meyer

Writing lesson: Build an efficiency argument from a bottleneck diagnosis through the training intervention to matched end-to-end quality/resource comparisons.

Scientific selection: Included for writing analysis only. Included in the complete official ICCV 2025 oral writing inventory. Scientific catalog membership and any promotion require separate review; this writing scan makes no promotion decision.

009 · ICCV 2025 oral · Writing-focused manuscript scan + selected visuals inspected

Image as an IMU: Estimating Camera Motion from a Single Motion-Blurred Image

Jerred Chen, Ronald Clark

Writing lesson: For inverse problems, place ambiguity resolution beside the main method and distinguish measured supervision from model-derived references.

Scientific selection: Included for writing analysis only. Included in the complete official ICCV 2025 oral writing inventory. Scientific catalog membership and any promotion require separate review; this writing scan makes no promotion decision.

010 · ICCV 2025 oral · Writing-focused manuscript scan + selected visuals inspected

TrajectoryCrafter: Redirecting Camera Trajectory for Monocular Videos via Diffusion Models

Mark Yu, Wenbo Hu, Jinbo Xing, Ying Shan

Writing lesson: Give incompatible evaluation regimes separate tables and explicitly explain what a metric cannot reward in a generative task.

Scientific selection: Included for writing analysis only. Included in the complete official ICCV 2025 oral writing inventory. Scientific catalog membership and any promotion require separate review; this writing scan makes no promotion decision.

011 · ICCV 2025 oral · Writing-focused manuscript scan + selected visuals inspected

RayZer: A Self-supervised Large View Synthesis Model

Hanwen Jiang, Hao Tan, Peng Wang, Haian Jin, Yue Zhao, Sai Bi, Kai Zhang, Fujun Luan, Kalyan Sunkavalli, Qixing Huang, Georgios Pavlakos

Writing lesson: Draw every information path in a self-supervised objective, then separate representation usefulness from external geometric accuracy.

Scientific selection: Included for writing analysis only. Included in the complete official ICCV 2025 oral writing inventory. Scientific catalog membership and any promotion require separate review; this writing scan makes no promotion decision.

012 · ICCV 2025 oral · Writing-focused manuscript scan + selected visuals inspected

EVER: Exact Volumetric Ellipsoid Rendering for Real-time View Synthesis

Alexander Mai, Peter Hedman, George Kopanas, Dor Verbin, David Futschik, Qiangeng Xu, Falko Kuester, Jonathan T. Barron, Yinda Zhang

Writing lesson: Use the smallest worked construction to explain an exact algorithm, then measure the failure mode separately from average image quality.

Scientific selection: Included for writing analysis only. Included in the complete official ICCV 2025 oral writing inventory. Scientific catalog membership and any promotion require separate review; this writing scan makes no promotion decision.

013 · ICCV 2025 oral · Writing-focused manuscript scan + selected visuals inspected

Self-Ensembling Gaussian Splatting for Few-Shot Novel View Synthesis

Chen Zhao, Xuan Wang, Tong Zhang, Saqib Javed, Mathieu Salzmann

Writing lesson: Draw stateful training buffers and identify the single inference model; separate scene-specific resource checks from dataset-wide accuracy claims.

Scientific selection: Included for writing analysis only. Included in the complete official ICCV 2025 oral writing inventory. Scientific catalog membership and any promotion require separate review; this writing scan makes no promotion decision.

014 · ICCV 2025 oral · Writing-focused manuscript scan + selected visuals inspected

Back on Track: Bundle Adjustment for Dynamic Scene Reconstruction

Weirong Chen, Ganlin Zhang, Felix Wimbauer, Rui Wang, Nikita Araslanov, Andrea Vedaldi, Daniel Cremers

Writing lesson: Use stage-specific contracts and tables to keep camera motion, object motion and depth quality from collapsing into one reconstruction claim.

Scientific selection: Included for writing analysis only. Included in the complete official ICCV 2025 oral writing inventory. Scientific catalog membership and any promotion require separate review; this writing scan makes no promotion decision.

015 · ICCV 2025 oral · Writing-focused manuscript scan + selected visuals inspected

SceneSplat: Gaussian Splatting-based Scene Understanding with Vision-Language Pretraining

Yue Li, Qi Ma, Runyi Yang, Huapeng Li, Mengjiao Ma, Bin Ren, Nikola Popovic, Nicu Sebe, Ender Konukoglu, Theo Gevers, Luc Van Gool, Martin R. Oswald, Danda Pani Paudel

Writing lesson: For joint data-and-method papers, expose conversion quality, teacher-label provenance and downstream evaluation regimes before summarizing gains.

Scientific selection: Included for writing analysis only. Included in the complete official ICCV 2025 oral writing inventory. Scientific catalog membership and any promotion require separate review; this writing scan makes no promotion decision.

016 · ICCV 2025 oral · Writing-focused manuscript scan + selected visuals inspected

Variance-Based Pruning for Accelerating and Compressing Trained Networks

Uranik Berisha, Jens Mehnert, Alexandru Paul Condurache

Writing lesson: Report intervention size, whole-model savings and immediate versus recovered accuracy as separate quantities.

Scientific selection: Included for writing analysis only. Included in the complete official ICCV 2025 oral writing inventory. Scientific catalog membership and any promotion require separate review; this writing scan makes no promotion decision.

017 · ICCV 2025 oral · Writing-focused manuscript scan + selected visuals inspected

Importance-Based Token Merging for Efficient Image and Video Generation

Haoyu Wu, Jingyi Xu, Hieu Le, Dimitris Samaras

Writing lesson: Use a small token identity trace to explain selection logic, and report efficiency under both optimized and unoptimized attention settings.

Scientific selection: Included for writing analysis only. Included in the complete official ICCV 2025 oral writing inventory. Scientific catalog membership and any promotion require separate review; this writing scan makes no promotion decision.

018 · ICCV 2025 oral · Writing-focused manuscript scan + selected visuals inspected

Knowledge Distillation for Learned Image Compression

Yunuo Chen, Zezheng Lyu, Bing He, Ning Cao, Gang Chen, Guo Lu, Wenjun Zhang

Writing lesson: Always retain teacher, un-distilled student and distilled student rows so architecture compression and supervision benefits cannot be confused.

Scientific selection: Included for writing analysis only. Included in the complete official ICCV 2025 oral writing inventory. Scientific catalog membership and any promotion require separate review; this writing scan makes no promotion decision.

019 · ICCV 2025 oral · Writing-focused manuscript scan + selected visuals inspected

Distilling Diffusion Models to Efficient 3D LiDAR Scene Completion

Shengyuan Zhang, An Zhao, Ling Yang, Zejian Li, Chenye Meng, Haoran Xu, Tianrun Chen, AnYang Wei, Perry Pengyun Gu, Lingyun Sun

Writing lesson: Pair an acceleration curve with a matched sampling-step control and keep auxiliary refinement visible in row labels.

Scientific selection: Included for writing analysis only. Included in the complete official ICCV 2025 oral writing inventory. Scientific catalog membership and any promotion require separate review; this writing scan makes no promotion decision.

020 · ICCV 2025 oral · Writing-focused manuscript scan + selected visuals inspected

Heavy Labels Out! Dataset Distillation with Label Space Lightening

Ruonan Yu, Songhua Liu, Zigeng Chen, Jingwen Ye, Xinchao Wang

Writing lesson: Audit all auxiliary assets behind a compact dataset claim and state whether storage is total, incremental or amortized over shared models.

Scientific selection: Included for writing analysis only. Included in the complete official ICCV 2025 oral writing inventory. Scientific catalog membership and any promotion require separate review; this writing scan makes no promotion decision.

021 · ICCV 2025 oral · Writing-focused manuscript scan + selected visuals inspected

RS-vHeat: Heat Conduction Guided Efficient Remote Sensing Foundation Model

Huiyang Hu, Peijin Wang, Hanbo Bi, Boyuan Tong, Zhaozhi Wang, Wenhui Diao, Hao Chang, Yingchao Feng, Ziqi Zhang, Yaowei Wang, Qixiang Ye, Kun Fu, Xian Sun

Writing lesson: For a physically inspired architecture, connect each analogy to an explicit computation and evaluate its resource advantage across input resolutions.

Scientific selection: Included for writing analysis only. Included in the complete official ICCV 2025 oral writing inventory. Scientific catalog membership and any promotion require separate review; this writing scan makes no promotion decision.

022 · ICCV 2025 oral · Writing-focused manuscript scan + selected visuals inspected

Towards a Unified Copernicus Foundation Model for Earth Vision

Yi Wang, Zhitong Xiong, Chenying Liu, Adam J. Stewart, Thomas Dujardin, Nikolaos Ioannis Bountos, Angelos Zavras, Franziska Gerken, Ioannis Papoutsis, Laura Leal-Taixé, Xiao Xiang Zhu

Writing lesson: For a data–model–benchmark package, give each deliverable a separate contract and preserve unsupported task cells instead of manufacturing a universal average.

Scientific selection: Included for writing analysis only. Included in the complete official ICCV 2025 oral writing inventory. Scientific catalog membership and any promotion require separate review; this writing scan makes no promotion decision.

023 · ICCV 2025 oral · Writing-focused manuscript scan + selected visuals inspected

Learning Streaming Video Representation via Multitask Training

Yibin Yan, Jilan Xu, Shangzhe Di, Yikun Liu, Yudi Shi, Qirui Chen, Zeqian Li, Yifei Huang, Weidi Xie

Writing lesson: Define online information access first, then separate representation training, task-head adaptation and end-to-end response cost.

Scientific selection: Included for writing analysis only. Included in the complete official ICCV 2025 oral writing inventory. Scientific catalog membership and any promotion require separate review; this writing scan makes no promotion decision.

024 · ICCV 2025 oral · Writing-focused manuscript scan + selected visuals inspected

LoftUp: Learning a Coordinate-Based Feature Upsampler for Vision Foundation Models

Haiwen Huang, Anpei Chen, Volodymyr Havrylov, Andreas Geiger, Dan Zhang

Writing lesson: When two ingredients improve together, cross the new objective with old architectures and the new architecture with fixed supervision.

Scientific selection: Included for writing analysis only. Included in the complete official ICCV 2025 oral writing inventory. Scientific catalog membership and any promotion require separate review; this writing scan makes no promotion decision.

025 · ICCV 2025 oral · Writing-focused manuscript scan + selected visuals inspected

Learning Visual Hierarchies in Hyperbolic Space for Image Retrieval

Ziwei Wang, Sameera Ramasinghe, Chenchen Xu, Julien Monteil, Loris Bazzani, Thalaiyasingam Ajanthan

Writing lesson: Define the hierarchy and asymmetric retrieval target operationally, and expose privileged regions in downstream evaluation captions.

Scientific selection: Included for writing analysis only. Included in the complete official ICCV 2025 oral writing inventory. Scientific catalog membership and any promotion require separate review; this writing scan makes no promotion decision.

026 · ICCV 2025 oral · Writing-focused manuscript scan + selected visuals inspected

GMMamba: Group Masking Mamba for Whole Slide Image Classification

Tingting Zheng, Hongxun Yao, Kui Jiang, Yi Xiao, Sicheng Zhao

Writing lesson: Keep patient/case counts, slide counts, patch scale and feature encoder separate, and state each ablation’s grouping/masking settings in its caption.

Scientific selection: Included for writing analysis only. Included in the complete official ICCV 2025 oral writing inventory. Scientific catalog membership and any promotion require separate review; this writing scan makes no promotion decision.

027 · ICCV 2025 oral · Writing-focused manuscript scan + selected visuals inspected

NullSwap: Proactive Identity Cloaking Against Deepfake Face Swapping

Tianyi Wang, Shuaicheng Niu, Harry Cheng, Xiao Zhang, Yinglong Wang

Writing lesson: State protection target and model-access assumptions before presenting defense scores, then separate imperceptibility from attack disruption.

Scientific selection: Included for writing analysis only. Included in the complete official ICCV 2025 oral writing inventory. Scientific catalog membership and any promotion require separate review; this writing scan makes no promotion decision.

028 · ICCV 2025 oral · Writing-focused manuscript scan + selected visuals inspected

MaskControl: Spatio-Temporal Control for Masked Motion Synthesis

Ekkasit Pinyoanuntapong, Muhammad Saleem, Korrawe Karunratanakul, Pu Wang, Hongfei Xue, Chen Chen, Chuan Guo, Junli Cao, Jian Ren, Sergey Tulyakov

Writing lesson: Separate training privileges, inference optimization and metric thresholds when reporting controllable generation.

Scientific selection: Included for writing analysis only. Included in the complete official ICCV 2025 oral writing inventory. Scientific catalog membership and any promotion require separate review; this writing scan makes no promotion decision.

029 · ICCV 2025 oral · Writing-focused manuscript scan + selected visuals inspected

HairCUP: Hair Compositional Universal Prior for 3D Gaussian Avatars

Byungjun Kim, Shunsuke Saito, Giljoo Nam, Tomas Simon, Jason Saragih, Hanbyul Joo, Junxuan Li

Writing lesson: Draw supervision provenance alongside compositional branches and use targeted visual ablations for boundary artifacts.

Scientific selection: Included for writing analysis only. Included in the complete official ICCV 2025 oral writing inventory. Scientific catalog membership and any promotion require separate review; this writing scan makes no promotion decision.

030 · ICCV 2025 oral · Writing-focused manuscript scan + selected visuals inspected

Understanding Co-speech Gestures in-the-wild

Sindhu B Hegde, K R Prajwal, Taein Kwon, Andrew Zisserman

Writing lesson: For weakly aligned modalities, visualize annotation-time boundaries against the event being localized and report task-specific non-wins.

Scientific selection: Included for writing analysis only. Included in the complete official ICCV 2025 oral writing inventory. Scientific catalog membership and any promotion require separate review; this writing scan makes no promotion decision.

031 · ICCV 2025 oral · Writing-focused manuscript scan + selected visuals inspected

DPoser-X: Diffusion Model as Robust 3D Whole-body Human Pose Prior

Junzhe Lu, Jing Lin, Hongkun Dou, Ailing Zeng, Yue Deng, Xian Liu, Zhongang Cai, Lei Yang, Yulun Zhang, Haoqian Wang, Ziwei Liu

Writing lesson: Show a counterexample to an attractive metric and report both average and best-of-many performance for ambiguous reconstruction.

Scientific selection: Included for writing analysis only. Included in the complete official ICCV 2025 oral writing inventory. Scientific catalog membership and any promotion require separate review; this writing scan makes no promotion decision.

032 · ICCV 2025 oral · Writing-focused manuscript scan + selected visuals inspected

Teeth Reconstruction and Performance Capture Using a Phone Camera

Weixi Zheng, Jingwang Ling, Zhibo Wang, Quan Wang, Feng Xu

Writing lesson: For accessible capture systems, disclose user interaction, calibration and optimization time, and separate synthetic geometric truth from real qualitative demonstrations.

Scientific selection: Included for writing analysis only. Included in the complete official ICCV 2025 oral writing inventory. Scientific catalog membership and any promotion require separate review; this writing scan makes no promotion decision.

033 · ICCV 2025 oral · Writing-focused manuscript scan + selected visuals inspected

Dynamic Typography: Bringing Text to Life via Video Diffusion Prior

Zichen Liu, Yihao Meng, Hao Ouyang, Yue Yu, Bolin Zhao, Daniel Cohen-Or, Huamin Qu

Writing lesson: Give each competing design requirement its own measurement and retain non-winning temporal scores alongside preference results.

Scientific selection: Included for writing analysis only. Included in the complete official ICCV 2025 oral writing inventory. Scientific catalog membership and any promotion require separate review; this writing scan makes no promotion decision.

034 · ICCV 2025 oral · Writing-focused manuscript scan + selected visuals inspected

Generating Physically Stable and Buildable Brick Structures from Text

Ava Pun, Kangle Deng, Ruixuan Liu, Deva Ramanan, Changliu Liu, Jun-Yan Zhu

Writing lesson: For constrained generation, report constraint satisfaction separately from similarity, state conditional metric denominators, and expose retry budgets.

Scientific selection: Included for writing analysis only. Included in the complete official ICCV 2025 oral writing inventory. Scientific catalog membership and any promotion require separate review; this writing scan makes no promotion decision.

035 · ICCV 2025 oral · Writing-focused manuscript scan + selected visuals inspected

WIR3D: Visually-Informed and Geometry-Aware 3D Shape Abstraction

Richard Liu, Daniel Fu, Noah Tan, Itai Lang, Rana Hanocka

Writing lesson: Introduce abstraction with a minimal counterexample, then distinguish geometric coverage, perceptual similarity and human preference.

Scientific selection: Included for writing analysis only. Included in the complete official ICCV 2025 oral writing inventory. Scientific catalog membership and any promotion require separate review; this writing scan makes no promotion decision.

036 · ICCV 2025 oral · Writing-focused manuscript scan + selected visuals inspected

SparseFlex: High-Resolution and Arbitrary-Topology 3D Shape Modeling

Xianglong He, Zi-Xin Zou, Chia-Hao Chen, Yuan-Chen Guo, Ding Liang, Chun Yuan, Wanli Ouyang, Yan-Pei Cao, Yangguang Li

Writing lesson: Keep reconstruction and generation evaluations separate, and report resource savings against resolution and visibility rather than one headline number.

Scientific selection: Included for writing analysis only. Included in the complete official ICCV 2025 oral writing inventory. Scientific catalog membership and any promotion require separate review; this writing scan makes no promotion decision.

037 · ICCV 2025 oral · Writing-focused manuscript scan + selected visuals inspected

ReCamMaster: Camera-Controlled Generative Rendering from A Single Video

Jianhong Bai, Menghan Xia, Xiao Fu, Xintao Wang, Lianrui Mu, Jinwen Cao, Zuozhu Liu, Haoji Hu, Xiang Bai, Pengfei Wan, Di Zhang

Writing lesson: Use matched diagrams and controlled ablations for conditioning alternatives, and qualify tempting application labels at the point of use.

Scientific selection: Included for writing analysis only. Included in the complete official ICCV 2025 oral writing inventory. Scientific catalog membership and any promotion require separate review; this writing scan makes no promotion decision.

038 · ICCV 2025 oral · Writing-focused manuscript scan + selected visuals inspected

Forecasting Continuous Non-Conservative Dynamical Systems in SO(3)

Lennart Bastian, Mohammad Rashed, Nassir Navab, Tolga Birdal

Writing lesson: Keep input-state estimation, dynamics forecasting and visualization-only privileged quantities explicit, and pair solver-complexity metrics with runtime.

Scientific selection: Included for writing analysis only. Included in the complete official ICCV 2025 oral writing inventory. Scientific catalog membership and any promotion require separate review; this writing scan makes no promotion decision.

039 · ICCV 2025 oral · Writing-focused manuscript scan + selected visuals inspected

Certifiably Optimal Anisotropic Rotation Averaging

Carl Olsson, Yaroslava Lochman, Johan Malmport, Christopher Zach

Writing lesson: When presenting certified optimization, show the certificate diagnostic next to task error and cost, and explain which modeling change breaks the old relaxation.

Scientific selection: Included for writing analysis only. Included in the complete official ICCV 2025 oral writing inventory. Scientific catalog membership and any promotion require separate review; this writing scan makes no promotion decision.

040 · ICCV 2025 oral · Writing-focused manuscript scan + selected visuals inspected

Deterministic Object Pose Confidence Region Estimation

Jinghao Wang, Zhang Li, Zi Wang, Banglei Guan, Yang Shang, Qifeng Yu

Writing lesson: Evaluate confidence regions with coverage, size and rejected/oversized-case counts, and distinguish calibrated input guarantees from downstream approximations.

Scientific selection: Included for writing analysis only. Included in the complete official ICCV 2025 oral writing inventory. Scientific catalog membership and any promotion require separate review; this writing scan makes no promotion decision.

041 · ICCV 2025 oral · Writing-focused manuscript scan + selected visuals inspected

RePoseD: Efficient Relative Pose Estimation With Known Depth Information

Yaqing Ding, Viktor Kocur, Václav Vávra, Zuzana Berger Haladová, Jian Yang, Torsten Sattler, Zuzana Kukelova

Writing lesson: For a family of geometric solvers, organize assumptions in a taxonomy and make performance recommendations conditional on measurement quality.

Scientific selection: Included for writing analysis only. Included in the complete official ICCV 2025 oral writing inventory. Scientific catalog membership and any promotion require separate review; this writing scan makes no promotion decision.

042 · ICCV 2025 oral · Writing-focused manuscript scan + selected visuals inspected

Diving into the Fusion of Monocular Priors for Generalized Stereo Matching

Chengtang Yao, Lidong Yu, Zhidan Liu, Jiaxi Zeng, Yuwei Wu, Yunde Jia

Writing lesson: Define evaluation masks and the source of reported dispersion, then separate inference-module ablations from retraining comparisons.

Scientific selection: Included for writing analysis only. Included in the complete official ICCV 2025 oral writing inventory. Scientific catalog membership and any promotion require separate review; this writing scan makes no promotion decision.

043 · ICCV 2025 oral · Writing-focused manuscript scan + selected visuals inspected

LaRender: Training-Free Occlusion Control in Image Generation via Latent Rendering

Xiaohang Zhan, Dingming Liu

Writing lesson: Define the visual relationship being controlled and pair a physical analogy with concrete failure categories and metric limitations.

Scientific selection: Included for writing analysis only. Included in the complete official ICCV 2025 oral writing inventory. Scientific catalog membership and any promotion require separate review; this writing scan makes no promotion decision.

044 · ICCV 2025 oral · Writing-focused manuscript scan + selected visuals inspected

MikuDance: Animating Character Art with Mixed Motion Dynamics

Jiaxu Zhang, Xianfang Zeng, Xin Chen, Wei Zuo, Gang Yu, Zhigang Tu

Writing lesson: For animation systems, distinguish reference-domain construction, paired quantitative tests and open-ended qualitative examples, and include a domain-fine-tuned baseline.

Scientific selection: Included for writing analysis only. Included in the complete official ICCV 2025 oral writing inventory. Scientific catalog membership and any promotion require separate review; this writing scan makes no promotion decision.

045 · ICCV 2025 oral · Writing-focused manuscript scan + selected visuals inspected

Diffusion Transformer meets Multi-level Wavelet Spectrum for Single Image Super-Resolution

Peng Du, Hui Li, Han Xu, Paul Barom Jeon, Dongwook Lee, Daehyun Ji, Ran Yang, Feng Zhu

Writing lesson: Use subset-qualified highlighting and separate distortion, perceptual quality and downstream identity claims in restoration tables.

Scientific selection: Included for writing analysis only. Included in the complete official ICCV 2025 oral writing inventory. Scientific catalog membership and any promotion require separate review; this writing scan makes no promotion decision.

046 · ICCV 2025 oral · Writing-focused manuscript scan + selected visuals inspected

LOTS of Fashion! Multi-Conditioning for Image Generation via Sketch-Text Pairing

Federico Girella, Davide Talon, Ziyue Liu, Zanxi Ruan, Yiming Wang, Marco Cristani

Writing lesson: For compositional control, report both desired-attribute presence and leakage, and show each baseline’s conditioning privileges.

Scientific selection: Included for writing analysis only. Included in the complete official ICCV 2025 oral writing inventory. Scientific catalog membership and any promotion require separate review; this writing scan makes no promotion decision.

047 · ICCV 2025 oral · Writing-focused manuscript scan + selected visuals inspected

FlowEdit: Inversion-Free Text-Based Editing Using Pre-Trained Flow Models

Vladimir Kulikov, Matan Kleiner, Inbar Huberman-Spiegelglas, Tomer Michaeli

Writing lesson: Re-express a familiar baseline before introducing a change, and use an exact-control experiment to isolate the mechanism from implementation error.

Scientific selection: Included for writing analysis only. Included in the complete official ICCV 2025 oral writing inventory. Scientific catalog membership and any promotion require separate review; this writing scan makes no promotion decision.

048 · ICCV 2025 oral · Writing-focused manuscript scan + selected visuals inspected

LayerTracer: Cognitive-Aligned Layered SVG Synthesis via Diffusion Transformer

Yiren Song, Danze Chen, Mike Zheng Shou

Writing lesson: Expose the learned raster-to-vector handoff and evaluate semantic layer organization separately from the final rendered image.

Scientific selection: Included for writing analysis only. Included in the complete official ICCV 2025 oral writing inventory. Scientific catalog membership and any promotion require separate review; this writing scan makes no promotion decision.

049 · ICCV 2025 oral · Writing-focused manuscript scan + selected visuals inspected

ROAR: Reducing Inversion Error in Generative Image Watermarking

Hanyi Wang, Han Fang, Shi-Lin Wang, Ee-Chien Chang

Writing lesson: Test the intermediate mechanism separately from the endpoint and report attack strength together with both recovery and image damage.

Scientific selection: Included for writing analysis only. Included in the complete official ICCV 2025 oral writing inventory. Scientific catalog membership and any promotion require separate review; this writing scan makes no promotion decision.

050 · ICCV 2025 oral · Writing-focused manuscript scan + selected visuals inspected

Moto: Latent Motion Token as the Bridging Language for Learning Robot Manipulation from Videos

Yi Chen, Yuying Ge, Weiliang Tang, Yizhuo Li, Yixiao Ge, Mingyu Ding, Ying Shan, Xihui Liu

Writing lesson: Make every change in supervision and observation privileges visible across pretraining, fine-tuning and evaluation.

Scientific selection: Included for writing analysis only. Included in the complete official ICCV 2025 oral writing inventory. Scientific catalog membership and any promotion require separate review; this writing scan makes no promotion decision.

051 · ICCV 2025 oral · Writing-focused manuscript scan + selected visuals inspected

Automated Model Evaluation for Object Detection via Prediction Consistency and Reliability

Seungju Yoo, Hyuk Kwon, Joong-Won Hwang, Kibok Lee

Writing lesson: Trace an evaluation proxy from individual predictions to the dataset-level target, and expose the calibration split and detector assumptions.

Scientific selection: Included for writing analysis only. Included in the complete official ICCV 2025 oral writing inventory. Scientific catalog membership and any promotion require separate review; this writing scan makes no promotion decision.

052 · ICCV 2025 oral · Writing-focused manuscript scan + selected visuals inspected

Counting Stacked Objects

Corentin Dumery, Noa Etté, Aoxiang Fan, Ren Li, Jingyi Xu, Hieu Le, Pascal Fua

Writing lesson: Factor a hidden-variable task into interpretable estimates and display intermediate values beside final errors, including the source of ground truth.

Scientific selection: Included for writing analysis only. Included in the complete official ICCV 2025 oral writing inventory. Scientific catalog membership and any promotion require separate review; this writing scan makes no promotion decision.

053 · ICCV 2025 oral · Writing-focused manuscript scan + selected visuals inspected

MIORe & VAR-MIORe: Benchmarks to Push the Boundaries of Restoration

George Ciubotariu, Zhuyun Zhou, Zongwei Wu, Radu Timofte

Writing lesson: For a benchmark paper, connect the motivating failure taxonomy to acquisition choices, target construction and stratified evaluation.

Scientific selection: Included for writing analysis only. Included in the complete official ICCV 2025 oral writing inventory. Scientific catalog membership and any promotion require separate review; this writing scan makes no promotion decision.

054 · ICCV 2025 oral · Writing-focused manuscript scan + selected visuals inspected

Soft Local Completeness: Rethinking Completeness in XAI

Ziv Weiss Haddad, Oren Barkan, Yehonatan Elisha, Noam Koenigstein

Writing lesson: Introduce an intuitive axiom with a counterexample, state where the toy argument stops applying, and triangulate its practical value with different evaluation notions.

Scientific selection: Included for writing analysis only. Included in the complete official ICCV 2025 oral writing inventory. Scientific catalog membership and any promotion require separate review; this writing scan makes no promotion decision.

055 · ICCV 2025 oral · Writing-focused manuscript scan + selected visuals inspected

SuperDec: 3D Scene Decomposition with Superquadrics Primitives

Elisabetta Fedele, Boyang Sun, Leonidas Guibas, Marc Pollefeys, Francis Engelmann

Writing lesson: Evaluate a compact representation on both its approximation error and its resource footprint, then label downstream demonstrations separately from core quantitative evidence.

Scientific selection: Included for writing analysis only. Included in the complete official ICCV 2025 oral writing inventory. Scientific catalog membership and any promotion require separate review; this writing scan makes no promotion decision.

056 · ICCV 2025 oral · Writing-focused manuscript scan + selected visuals inspected

Diffusion Image Prior

Hamadi Chihaoui, Paolo Favaro

Writing lesson: Explain a stopping rule with paired observable and oracle trajectories, then quantify both its parameter sensitivity and its gap to the oracle.

Scientific selection: Included for writing analysis only. Included in the complete official ICCV 2025 oral writing inventory. Scientific catalog membership and any promotion require separate review; this writing scan makes no promotion decision.

057 · ICCV 2025 oral · Writing-focused manuscript scan + selected visuals inspected

Spatially-Varying Autofocus

Yingsi Qin, Aswin C. Sankaranarayanan, Matthew O'Toole

Writing lesson: A computational-imaging paper benefits from a clean separation of optical capture, control computation and post-processing, with each baseline’s acquisition budget shown.

Scientific selection: Included for writing analysis only. Included in the complete official ICCV 2025 oral writing inventory. Scientific catalog membership and any promotion require separate review; this writing scan makes no promotion decision.

058 · ICCV 2025 oral · Writing-focused manuscript scan + selected visuals inspected

Towards Foundational Models for Single-Chip Radar

Tianshu Huang, Akarsh Prabhakara, Chuhan Chen, Jay Karhade, Deva Ramanan, Matthew O'toole, Anthony Rowe

Writing lesson: State the actual independent evaluation unit and the dependence correction before showing confidence intervals; distinguish observed scaling from extrapolated requirements.

Scientific selection: Included for writing analysis only. Included in the complete official ICCV 2025 oral writing inventory. Scientific catalog membership and any promotion require separate review; this writing scan makes no promotion decision.

059 · ICCV 2025 oral · Writing-focused manuscript scan + selected visuals inspected

Event-based Visual Vibrometry

Xinyu Zhou, Peiqi Duan, Yeliduosi Xiaokaiti, Chao Xu, Boxin Shi

Writing lesson: For a sensing pipeline, separately validate the estimated intermediate signal and the downstream physical inference, naming the provenance of each reference measurement.

Scientific selection: Included for writing analysis only. Included in the complete official ICCV 2025 oral writing inventory. Scientific catalog membership and any promotion require separate review; this writing scan makes no promotion decision.

060 · ICCV 2025 oral · Writing-focused manuscript scan + selected visuals inspected

CorrCLIP: Reconstructing Patch Correlations in CLIP for Open-Vocabulary Semantic Segmentation

Dengke Zhang, Fagui Liu, Quan Tang

Writing lesson: Distinguish which interactions are allowed from how strongly they are weighted, and connect each named component to a diagnostic or ablation.

Scientific selection: Included for writing analysis only. Included in the complete official ICCV 2025 oral writing inventory. Scientific catalog membership and any promotion require separate review; this writing scan makes no promotion decision.

061 · ICCV 2025 oral · Writing-focused manuscript scan + selected visuals inspected

E-SAM: Training-Free Segment Every Entity Model

Weiming Zhang, Dingwen Xiao, Lei Chen, Lin Wang

Writing lesson: Tie each post-processing module to a visible failure mode and disclose its extra inference work alongside training-free claims.

Scientific selection: Included for writing analysis only. Included in the complete official ICCV 2025 oral writing inventory. Scientific catalog membership and any promotion require separate review; this writing scan makes no promotion decision.

062 · ICCV 2025 oral · Writing-focused manuscript scan + selected visuals inspected

Online Reasoning Video Segmentation with Just-in-Time Digital Twins

Yiqing Shen, Bohan Liu, Chenjia Li, Lalithkumar Seenivasan, Mathias Unberath

Writing lesson: For an agent system, show the planning/execution boundary and the maintained state, then evaluate both task complexity and component dependence.

Scientific selection: Included for writing analysis only. Included in the complete official ICCV 2025 oral writing inventory. Scientific catalog membership and any promotion require separate review; this writing scan makes no promotion decision.

063 · ICCV 2025 oral · Writing-focused manuscript scan + selected visuals inspected

Easy3D: A Simple Yet Effective Method for 3D Interactive Segmentation

Andrea Simonelli, Norman Müller, Peter Kontschieder

Writing lesson: In interactive-method papers, make the feedback policy part of the experimental definition and show how each added interaction changes the output.

Scientific selection: Included for writing analysis only. Included in the complete official ICCV 2025 oral writing inventory. Scientific catalog membership and any promotion require separate review; this writing scan makes no promotion decision.

064 · ICCV 2025 oral · Writing-focused manuscript scan + selected visuals inspected

ForestFormer3D: A Unified Framework for End-to-End Segmentation of Forest LiDAR 3D Point Clouds

Binbin Xiang, Maciej Wielgosz, Stefano Puliti, Kamil Král, Martin Krůček, Azim Missarov, Rasmus Astrup

Writing lesson: For a specialized domain, connect acquisition geometry to model and inference design, and keep competing task outcomes visible in the main table.

Scientific selection: Included for writing analysis only. Included in the complete official ICCV 2025 oral writing inventory. Scientific catalog membership and any promotion require separate review; this writing scan makes no promotion decision.