Writing study: Counting Stacked Objects

ICCV overviewCorpus atlasBy contribution typeVisual galleryRules & templateWriting patternsPaper studies

← ICCV 2025 oral writing corpus

Corentin Dumery, Noa Etté, Aoxiang Fan, Ren Li, Jingyi Xu, Hieu Le, Pascal Fua · 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: Domain-grounded methods & physical systems (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

≈ 8.14 page-equivalents

Main figures / tables

9 / 5

Attached appendix figures / tables

0 / 0

Attached appendix span

No boundary detected; not assumed zero

Before references / appendix: ≈ 81.4%References / intervening material: ≈ 18.6%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.

Source-bound correction: A trailing period does not turn the numbered acknowledgment into a scientific section.

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	2	≈ 0.48 pp.	4.8%
3. Method	3	≈ 2.66 pp.	26.6%
4. Experiments	5	≈ 2.97 pp.	29.7%
5. Conclusion	8	≈ 0.25 pp.	2.5%
6. Acknowledgements.	9	≈ 0.09 pp.	0.9%
References	9	≈ 1.86 pp.	18.6%

All detected figure and table locations

Main text

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

Attached appendix

No recognized caption labels.

Argument and organization

1. 1 Introduction; 2 Related Work

   Distinguishes counting mostly hidden objects from detecting all visible instances.

2. 3 Method

   Factorizes count into stack volume, occupancy ratio and unit volume, with synthetic occupancy training and multi-view reconstruction.

3. 4 Experiments; 5 Conclusion

   Separates end-to-end counting from occupancy estimation, compares human/vision baselines and studies depth/shape sensitivity.

Problem, claim and contribution

The problem is explicitly nearly-identical stacked objects with sufficient visible examples, not arbitrary heterogeneous hidden contents.

Sections 3 and 5, physical pp.3,8 · Main paper

Argument and section order

The count equation motivates separate learned occupancy and reconstructed volume pathways; unit-object volume and scale reference are treated as required inputs or estimation steps.

Sections 3.1–3.3, pp.3–5 · Main paper

Figures, captions and visual explanation

The pipeline separates the key-view occupancy branch from multi-view geometry; intermediate examples show template geometry, overall reconstruction and count error together.

Figure 2, p.2; Figure 7, p.7 · Main paper

Tables, comparisons and evidence

Metrics include normalized errors because scene counts vary greatly; human average error is distinguished from the error of the averaged human guess.

Sections 4.1–4.2 and Tables 1–3, p.6 · Main paper

Appendix and reproducibility

Architecture details, extra dataset examples, metrics and qualitative results are routed to supplementary material, not inspected.

Sections 3.2 and 4, pp.3–6 · Main paper

Clarity and writing conventions

The limitations explicitly acknowledge lack of individual-instance localization and degradation with geometric or visual complexity.

Section 4.5 and conclusion, p.8 · Main paper

What to reuse—and what not to infer

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

Boundary: The system needs multiple views, object/unit-volume information and scale calibration; it does not count arbitrary hidden objects from one casual photo. Real scenes number 45, counts above 500 are weight-inferred, and aggregate occupancy cannot reveal exact buried arrangement or identify every instance.

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

2, 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 · 10 pages