Writing study: Diving into the Fusion of Monocular Priors for Generalized Stereo Matching

ICCV overviewCorpus atlasBy contribution typeVisual galleryRules & templateWriting patternsPaper studies

← ICCV 2025 oral writing corpus

Chengtang Yao, Lidong Yu, Zhidan Liu, Jiaxi Zeng, Yuwei Wu, Yunde Jia · 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: Architecture & representation (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

11 physical pages

Before references / appendix

≈ 8.05 page-equivalents

Main figures / tables

4 / 7

Attached appendix figures / tables

0 / 0

Attached appendix span

No boundary detected; not assumed zero

Before references / appendix: ≈ 73.18%References / intervening material: ≈ 26.82%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	≈ 1.37 pp.	12.45%
2. Related Work	3	≈ 0.57 pp.	5.18%
3. Method	3	≈ 1.93 pp.	17.55%
4. Experiments	5	≈ 3.17 pp.	28.82%
5. Conclusion	8	≈ 0.33 pp.	3%
References	9	≈ 2.95 pp.	26.82%

All detected figure and table locations

Main text

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

Attached appendix

No recognized caption labels.

Argument and organization

1. 1 Introduction; 2 Related Work

   Identifies early noisy disparity and monocular scale ambiguity as separate obstacles to fusion.

2. 3 Method

   Defines relative ordering, iterative local guidance and final pixel-wise registration/confidence fusion.

3. 4 Experiments; 5 Conclusion

   Specifies region masks and generalization splits before modular and configuration ablations.

Problem, claim and contribution

The paper argues that a strong monocular prior still needs compatible representation and noise-aware fusion with binocular disparity.

Sections 1 and 3.2–3.3, physical pp.1–2,3–5 · Main paper

Argument and section order

Local relative ordering is used during iterative matching, while global registration is deferred until the disparity is refined.

Sections 3.2–3.3, pp.3–5 · Main paper

Figures, captions and visual explanation

The pipeline expands local and global fusion in separate colored boxes and defines every operation symbol in the caption.

Figure 2, p.4 · Main paper

Tables, comparisons and evidence

Evaluation explicitly distinguishes all, non-occluded, occluded and transparent regions; component ablations are trained from scratch, and displayed dispersion comes from training checkpoints.

Section 4.2, pp.5–6; Tables 4–7 and Section 4.4, p.7 · Main paper

Appendix and reproducibility

Additional visualizations, failure cases and future-work discussion are assigned to supplementary material rather than detailed in the main conclusion; those were not inspected.

Sections 4.3–4.4, pp.6–8 · Main paper

Clarity and writing conventions

The monocular comparison labels ground-truth scale alignment explicitly, preventing privileged registration from being mistaken for an operational prediction.

Table 4, p.7 · Main paper

What to reuse—and what not to infer

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

Boundary: No additional stereo data does not mean no external pretrained supervision: DepthAnything V2 is frozen. The repeated “unbiased” prior language is stronger than tested cross-domain performance; checkpoint variation is not independent-seed uncertainty, and 0.32 to 0.40 seconds is a measurable relative overhead despite the “barely” wording.

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

4, 7

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 · 11 pages