Writing study: Learning Convex Decomposition via Feature Fields

CVPR overviewCorpus atlasBy contribution typeVisual galleryRules & templateWriting patternsPaper studies

← CVPR 2026 oral writing corpus

Yuezhi Yang, Qixing Huang, Mikaela Angelina Uy, Nicholas Sharp · Official CVPR 2026 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: Training, objectives & optimization (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

≈ 8.11 page-equivalents

Main figures / tables

11 / 2

Attached appendix figures / tables

0 / 0

Attached appendix span

Separate file recorded below; not in this PDF total

Before references / appendix: ≈ 73.73%References / intervening material: ≈ 26.27%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	≈ 1.23 pp.	11.18%
2. Related Work	2	≈ 0.53 pp.	4.82%
3. Method	3	≈ 2.81 pp.	25.55%
4. Experiments	5	≈ 2.95 pp.	26.82%
5. Limitations and Future Work	8	≈ 0.27 pp.	2.45%
References	9	≈ 2.89 pp.	26.27%

All detected figure and table locations

Main text

• Figure 1 · p. 1
• Figure 2 · p. 2
• Figure 3 · p. 4
• Figure 4 · p. 4
• Figure 5 · p. 5
• Figure 6 · p. 5
• Figure 7 · p. 6
• Figure 8 · p. 7
• Table 1 · p. 7
• Table 2 · p. 8
• Figure 9 · p. 8
• Figure 10 · p. 8
• Figure 11 · p. 8

Attached appendix

No recognized caption labels.

Separate source files—excluded from canonical-PDF totals

A separate author version may repeat main text and references. Whole-file lengths and counts are not extra appendix material and are never added to the canonical PDF totals. Read the study's source scope for which sections received substantive reading versus layout inspection.

Additional source 1

Separate PDF (or ZIP containing it): whole-file layout of 3 physical pages; 0 detected figures and 2 tables. These may include overlapping main-text material.

Located appendix only: starts on physical p.1; ≈ 2.88 page-equivalents, 0 figure labels and 2 table labels. This interval is distinct from the whole file.

Detected heading	PDF page	Estimated span
Supplementary Material	1	≈ 0.17 pp.
A. Implementation Details	1	≈ 2.71 pp.

• Table 3 · p. 2
• Table 4 · p. 2

Argument and organization

1. 3. Method

   Moves from convexity formulation to feature learning, triplet construction, and feed-forward inference.

2. 4. Evaluation and 5. Limitations

   Compares fidelity/granularity, ablates the objective, and discusses broader inputs and limits.

Problem, claim and contribution

The task is tied to efficient collision proxies, and the teaser shows input shape, feature field, and final convex pieces.

Figure 1 p. 1 · Main paper · Additional source 2

Argument and section order

A geometric definition motivates the objective before architecture; recursive decomposition is given as an explicit algorithm.

§§3.1–3.4; Algorithm 1 p. 6 · Main paper · Additional source 2

Figures, captions and visual explanation

The overview forks the same learned field into training and inference; a separate ray-sampling sketch explains positive and hard-negative pairs.

Figures 3–4 p. 4 · Main paper · Additional source 2

Tables, comparisons and evidence

The main table reports component count, concavity, and reconstruction error together, preventing fewer pieces alone from being treated as success.

Table 1 p. 7; Figure 7 p. 6 · Main paper · Additional source 2

Appendix and reproducibility

Runtime is reported separately with a nuanced comparison: faster than optimization-based alternatives but slower than another feed-forward model.

Supplement §C and Table 3 p. 2 · Main paper · Additional source 2

Clarity and writing conventions

Feature-field colors are explicitly identified as PCA visualization, not physical labels or decomposition ground truth.

Figure 3 caption p. 4; Figure 11 · Main paper · Additional source 2

What to reuse—and what not to infer

Transferable lesson: For geometric learning, connect the mathematical property to a sampling diagram and evaluate fidelity against representation complexity.

Boundary: An attractive colored partition is not a quantitative convexity guarantee; retain concavity and reconstruction metrics and granularity settings.

Apply this lesson using the argument and evidence worksheet.

Inspection record and sources

Checked

2026-09-26

Reading status

Writing-focused manuscript scan + selected visuals inspected

Main text

Manuscript-wide writing scan of main PDF pp. 1–8: framing, section structure, method exposition, figure/table captions, evaluation organization and conclusions; not an exhaustive technical proof audit or reproduction.

Appendix / supplement

Scanned three supplementary pages covering sampling/preprocessing, metric definitions, baseline settings, runtime, objective alternatives, and additional decompositions.

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 CVPR 2026 CVF proceedings PDF; retrieved 2026-09-26 · 11 pages
• Official CVPR 2026 separate supplementary PDF; retrieved 2026-09-26 · 3 pages