Writing study: Native and Compact Structured Latents for 3D Generation

CVPR overviewCorpus atlasBy contribution typeVisual galleryRules & templateWriting patternsPaper studies

← CVPR 2026 oral writing corpus

Jianfeng XIANG, Xiaoxue Chen, Sicheng Xu, Ruicheng Wang, Zelong Lv, Yu Deng, Hongyuan Zhu, Yue Dong, Hao Zhao, Nicholas Jing Yuan, Jiaolong Yang · 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

11 physical pages

Before references / appendix

≈ 8.05 page-equivalents

Main figures / tables

8 / 3

Attached appendix figures / tables

0 / 0

Attached appendix span

Separate file recorded below; not in this PDF total

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	≈ 0.8 pp.	7.27%
2. Related Work	2	≈ 0.64 pp.	5.82%
3. Method	3	≈ 2.93 pp.	26.64%
4. Experiments	6	≈ 2.59 pp.	23.55%
5. Conclusion	8	≈ 0.21 pp.	1.91%
References	9	≈ 2.95 pp.	26.82%

All detected figure and table locations

Main text

• Figure 1 · p. 1
• Figure 2 · p. 3
• Figure 3 · p. 3
• Figure 4 · p. 5
• Figure 5 · p. 7
• Figure 6 · p. 7
• Figure 7 · p. 7
• Table 1 · p. 8
• Table 2 · p. 8
• Table 3 · p. 8
• Figure 8 · 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 15 physical pages; 6 detected figures and 4 tables. These may include overlapping main-text material.

Located appendix only: starts on physical p.2; ≈ 13.95 page-equivalents, 6 figure labels and 4 table labels. This interval is distinct from the whole file.

Detected heading	PDF page	Estimated span
A. More Implementation Details	2	≈ 12 pp.
References	14	≈ 1.95 pp.

• Table 1 · p. 4
• Table 2 · p. 4
• Figure 1 · p. 5
• Table 3 · p. 5
• Figure 2 · p. 7
• Table 4 · p. 8
• Figure 3 · p. 10
• Figure 4 · p. 11
• Figure 5 · p. 12
• Figure 6 · p. 13

Argument and organization

1. Representation then compression

   Define O-Voxel shape/material fields before the sparse VAE.

2. Generator then distinct evidence

   Describe staged generation and separately evaluate reconstruction, generation, texture and scaling.

Problem, claim and contribution

The opening links complex topology, enclosed geometry and material detail to representational limitations, rather than treating generation quality as only model scale.

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

Argument and section order

Shape, material, VAE and generation are explicitly nested subsections, allowing readers to identify which layer of the system each result tests.

Sections 3.1–3.3, PDF pp. 3–6 · Main paper · Additional source 2

Figures, captions and visual explanation

Page 3 pairs a short representation-to-generation overview with a detailed bidirectional conversion diagram. Shape and material paths are boxed separately and tied to feature tuples.

Figures 2–3, PDF p. 3; visual inspection · Main paper · Additional source 2

Tables, comparisons and evidence

The reconstruction table reports token count, latent dimensionality, downsampling and decoding time alongside fidelity, while generation and architecture ablations are separate tables.

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

Appendix and reproducibility

Conversion pseudocode, sparse-convolution backend benchmarks, data preparation, evaluation protocol and limitations are indexed before the extended galleries.

Supplement contents and Sections A–F, PDF pp. 1–13 · Main paper · Additional source 2

Clarity and writing conventions

The evaluation explicitly distinguishes internal-mesh distance from visible-surface point sampling, clarifying which geometric errors each metric can see.

Section 4.1, PDF p. 6 · Main paper · Additional source 2

What to reuse—and what not to infer

Transferable lesson: For a multi-stage representation system, provide both an overview and a reversible-data-conversion diagram, then evaluate each layer with the appropriate fidelity and cost metric.

Boundary: Compact token count alone is incomplete without channel dimensionality and compute. Arbitrary-topology language remains bounded by voxel resolution and close-surface aliasing discussed in the supplement.

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. 1–11: 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. 1–15, 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 contents and Sections A–F, PDF pp. 1–13. 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 · 11 pages
• Official CVPR 2026 CVF supplementary PDF; retrieved 2026-09-26 · 15 pages