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

ICCV overviewCorpus atlasBy contribution typeVisual galleryRules & templateWriting patternsPaper studies

← ICCV 2025 oral writing corpus

George Ciubotariu, Zhuyun Zhou, Zongwei Wu, Radu Timofte · Official ICCV 2025 oral record

Observed writing choices, not acceptance rules. This study examines the inspected manuscript version. It does not establish why the paper was accepted or that its presentation choices should be copied unchanged.

Figure, table and section ledger

Editorial contribution type: Datasets, benchmarks & measurement (primary).

Layout extraction, not a required paper template. Counts are distinct caption labels; a multi-panel figure counts once. Section spans are estimated from heading positions, including floats and whitespace. Method and limitations.

Canonical PDF

10 physical pages

Before references / appendix

≈ 8.05 page-equivalents

Main figures / tables

9 / 6

Attached appendix figures / tables

0 / 0

Attached appendix span

No boundary detected; not assumed zero

Before references / appendix: ≈ 80.5%References / intervening material: ≈ 19.5%Estimated layout envelopes, not text/artwork area. Unresolved appendix boundaries remain within the undivided post-body material.

Extraction notes: No attached appendix boundary detected. Zero means no recognized caption, not independently verified absence.

Section-by-section lengths and source pages

The title/abstract/front matter precede the first numbered heading. A span ends at the next detected top-level heading, not at the last sentence; end-page whitespace is included. References and statements are listed separately. These are not measurements of text-only or artwork area.

Top-level heading	Starts on PDF page	Estimated span	Share of entire PDF
1. Introduction	1	≈ 1.28 pp.	12.8%
2. Related Work	3	≈ 0.77 pp.	7.7%
3. Motivation of Our Proposed Datasets	3	≈ 1.31 pp.	13.1%
4. Our MIORe & VAR-MIORe Datasets	5	≈ 2.21 pp.	22.1%
5. Experiments and Benchmarking	7	≈ 1.41 pp.	14.1%
6. Conclusions	8	≈ 0.27 pp.	2.7%
References	9	≈ 1.95 pp.	19.5%

All detected figure and table locations

Main text

• Figure 1 · p. 1
• Figure 2 · p. 3
• Figure 3 · p. 4
• Figure 4 · p. 4
• Figure 5 · p. 4
• Figure 6 · p. 5
• Figure 7 · p. 6
• Table 1 · p. 6
• Figure 8 · p. 7
• Figure 9 · p. 7
• Table 2 · p. 7
• Table 3 · p. 8
• Table 4 · p. 8
• Table 5 · p. 8
• Table 6 · p. 8

Attached appendix

No recognized caption labels.

Argument and organization

1. 1 Introduction; 2 Related Works; 3 Motivations

   Builds an acquisition-gap taxonomy across camera motion, scene motion, imaging conditions and environment.

2. 4 MIORe and VAR-MIORe Datasets

   Turns that taxonomy into high-frame-rate capture, motion-adaptive frame averaging and dataset statistics.

3. 5 Experiments and Benchmarking; 6 Conclusions

   Separates deblurring, interpolation and preliminary optical-flow evaluations with motion-stratified results.

Problem, claim and contribution

The benchmark gap is specified in terms of motion and imaging conditions rather than dataset size alone.

Section 3, physical pp.3–4 · Main paper

Argument and section order

Capture equipment, construction procedure and statistics precede task-specific evaluation, enabling readers to connect an acquisition decision to each target.

Sections 4.1–4.4, pp.5–7 · Main paper

Figures, captions and visual explanation

The motion montage distinguishes ego-camera from scene motion, while the dataset table places acquisition and effective frame rates in separate entries.

Figure 7 and Table 1, p.6 · Main paper

Tables, comparisons and evidence

VAR-MIORe tables vary temporal span explicitly; the deblurring caption states 333 inputs per bucket and interpolation includes the average-input baseline.

Tables 3 and 5, p.8 · Main paper

Appendix and reproducibility

Acquisition quality assurance, further plots and limitations are directed to supplementary material, which was not inspected.

Sections 4.2 and 5, pp.6–8 · Main paper

Clarity and writing conventions

Optical-flow results are expressly labeled preliminary, evaluated against pseudo-ground truth and in need of further refinement.

Section 5.3, p.8 · Main paper

What to reuse—and what not to infer

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

Boundary: More than a million captured frames come from 333 selected sequences, not independent scenes per frame. Blurry inputs are synthesized by averaging high-speed frames; optical-flow targets are estimated pseudo-ground truth. These distinctions constrain claims about naturally captured degradation and objective flow accuracy.

Apply this lesson using the argument and evidence worksheet.

Inspection record and sources

Checked

2026-10-07

Reading status

Writing-focused manuscript scan + selected visuals inspected

Main text

Writing-oriented scan across the main manuscript, physical PDF pp.1–8, covering framing, section progression, method explanations, captions, comparison protocols and concluding scope; reference boundary checked. Selected full-page rasters were inspected. Not exhaustive line-by-line reading, proof verification or experimental reproduction.

Appendix / supplement

Main-paper appendix/supplement references were checked. A separate supplementary source is linked in the inventory but was not retrieved or inspected; its contents are not included in the reading or visual-page counts.

Visually inspected PDF pages

6, 8

This is a writing-focused scan of the manuscript and the stated supplementary scope: framing, organization, visual explanation, evidence presentation and wording. It is not a line-by-line proof audit, reproduction of results or exhaustive scientific review.

• Official CVF open-access ICCV 2025 accepted-paper PDF, retrieved 7 October 2026; CVF states identical to accepted version except watermark; not assumed identical to initial submission · 10 pages