Writing study: S^2AM3D: Scale-controllable Part Segmentation of 3D Point Clouds

CVPR overviewCorpus atlasBy contribution typeVisual galleryRules & templateWriting patternsPaper studies

← CVPR 2026 oral writing corpus

Han Su, Tianyu Huang, Zichen Wan, Xiaohe Wu, Wangmeng Zuo · 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: 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

10 physical pages

Before references / appendix

≈ 8.1 page-equivalents

Main figures / tables

7 / 3

Attached appendix figures / tables

0 / 0

Attached appendix span

Separate file recorded below; not in this PDF total

Before references / appendix: ≈ 81%References / intervening material: ≈ 19%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	≈ 1.09 pp.	10.9%
2. Related Work	2	≈ 0.77 pp.	7.7%
3. Method	3	≈ 1.99 pp.	19.9%
4. Dataset Curation	5	≈ 0.68 pp.	6.8%
5. Experiments	5	≈ 2.94 pp.	29.4%
6. Conclusion	8	≈ 0.24 pp.	2.4%
Acknowledgements	9	≈ 0.05 pp.	0.5%
References	9	≈ 1.9 pp.	19%

All detected figure and table locations

Main text

• Figure 1 · p. 1
• Figure 2 · p. 3
• Figure 3 · p. 5
• Figure 4 · p. 6
• Table 1 · p. 6
• Figure 5 · p. 7
• Table 2 · p. 7
• Figure 6 · p. 8
• Figure 7 · p. 8
• Table 3 · 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; 2 detected figures and 3 tables. These may include overlapping main-text material.

Located appendix only: starts on physical p.1; ≈ 2.94 page-equivalents, 2 figure labels and 3 table labels. This interval is distinct from the whole file.

Detected heading	PDF page	Estimated span
Supplementary Material	1	≈ 0.07 pp.
1. Implementation Details	1	≈ 0.77 pp.
2. Additional Experiments	1	≈ 0.64 pp.
3. More Visualization Results	2	≈ 0.06 pp.
References	2	≈ 1.4 pp.

• Figure 1 · p. 1
• Table 1 · p. 2
• Table 2 · p. 2
• Table 3 · p. 3
• Figure 2 · p. 3

Argument and organization

1. Hybrid supervision and scale control

   Motivate 2D/3D consistency, then define encoder, prompt decoder and decoupled training.

2. Dataset and two evaluation modes

   Describe annotation curation before interactive and full-segmentation tests.

Problem, claim and contribution

The paper contrasts data-limited native 3D learning with inconsistent lifted 2D priors, motivating a hybrid training contract rather than choosing either extreme.

Introduction and Figure 1, PDF pp. 1–2 · Main paper · Additional source 2

Argument and section order

The task definition introduces both point index and optional scale, and the method separates encoder learning from later decoder training with the encoder frozen.

Sections 3.1 and 3.4, PDF pp. 3–4 · Main paper · Additional source 2

Figures, captions and visual explanation

The architecture divides encoder and scale-aware decoder with a clear boundary and frozen/trainable legend; the result grid and table separately label with-scale and no-scale variants.

Figure 2, PDF p. 3; Figure 4 and Table 1, PDF p. 6; visual inspection · Main paper · Additional source 2

Tables, comparisons and evidence

Interactive and full segmentation receive separate tables, while ablations preserve the distinction between supplied scale and no-scale testing.

Tables 1–3, PDF pp. 6–8 · Main paper · Additional source 2

Appendix and reproducibility

The supplement discloses that controlled scale tests use ground-truth part size, then probes perturbations and illustrates failures on thin structures and color-dependent distinctions.

Supplement Sections 2.3–2.4 and Figure 1, PDF pp. 1–3 · Main paper · Additional source 2

Clarity and writing conventions

The main text reuses scale, prompt and feature terminology consistently between the formal task, diagram and experiments.

Sections 3 and 5, PDF pp. 3–8 · Main paper · Additional source 2

What to reuse—and what not to infer

Transferable lesson: If an extra prompt improves performance, make its information advantage visible in every comparison and test sensitivity to imperfect user input.

Boundary: Ground-truth scale is privileged information relative to point-only baselines; the with-scale score should not be presented as a like-for-like automatic gain.

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 PDF pp. 1–10: framing, argument sequence, section organization, figure/table captions, evaluation interpretation and limitations; reference sections identified. This is a writing-focused scan, not an exhaustive technical proof or reproduction audit. Main PDF pages 3 and 6 were rendered and visually inspected.

Appendix / supplement

Writing-focused scan of the separate supplementary PDF, pp. 1–3, including its organization, captions, protocol/evidence detail and limitation material where present; proofs and code listings were inspected for exposition, not independently verified or executed. Supplement Sections 2.3–2.4 and Figure 1, PDF pp. 1–3. Linked video/audio demonstrations and non-PDF archive contents were not assessed.

Visually inspected PDF pages

3, 6

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 open-access accepted manuscript; retrieved 2026-09-26 · 10 pages
• Official CVPR 2026 CVF supplementary PDF; retrieved 2026-09-26 · 3 pages