Writing study: 3DReflecNet: A Large-Scale Dataset for 3D Reconstruction of Reflective, Transparent, and Low-Texture Objects

CVPR overviewCorpus atlasBy contribution typeVisual galleryRules & templateWriting patternsPaper studies

← CVPR 2026 oral writing corpus

Zhicheng Liang, Haoyi Yu, Boyan Li, Dayou Zhang, Zijian Cao, Tianyi Gong, Junhua Liu, Shuguang Cui, Fangxin Wang · 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: Datasets, benchmarks & measurement (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

12 physical pages

Before references / appendix

≈ 8.17 page-equivalents

Main figures / tables

12 / 5

Attached appendix figures / tables

0 / 0

Attached appendix span

Separate file recorded below; not in this PDF total

Before references / appendix: ≈ 68.08%References / intervening material: ≈ 31.92%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	2	≈ 0.68 pp.	5.67%
2. Related Works	2	≈ 0.82 pp.	6.83%
3. Observations and Motivation	3	≈ 0.74 pp.	6.17%
4. Dataset Construction and Statistics	4	≈ 2.43 pp.	20.25%
5. Experiments	6	≈ 1.78 pp.	14.83%
6. Discussions	8	≈ 0.2 pp.	1.67%
7. Conclusion	8	≈ 0.37 pp.	3.08%
References	9	≈ 3.83 pp.	31.92%

All detected figure and table locations

Main text

• Figure 1 · p. 1
• Figure 2 · p. 2
• Figure 3 · p. 3
• Figure 4 · p. 3
• Figure 5 · p. 4
• Table 1 · p. 5
• Figure 6 · p. 5
• Table 2 · p. 5
• Figure 7 · p. 6
• Figure 8 · p. 6
• Figure 9 · p. 6
• Figure 10 · p. 6
• Figure 11 · p. 7
• Table 3 · p. 7
• Table 4 · p. 7
• Table 5 · p. 7
• Figure 12 · 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 18 physical pages; 16 detected figures and 9 tables. These may include overlapping main-text material.

Located appendix only: starts on physical p.1; ≈ 17.85 page-equivalents, 16 figure labels and 9 table labels. This interval is distinct from the whole file.

Detected heading	PDF page	Estimated span
Supplementary Material	1	≈ 0.04 pp.
A. Web Interface and Dataset Access	1	≈ 0.07 pp.
B. Instance Breakdown	1	≈ 0.33 pp.
C. Near-Field Illumination	1	≈ 0.13 pp.
D. Assets Generation using 2D image	1	≈ 10.07 pp.
References	11	≈ 7.22 pp.

• Figure 1 · p. 2
• Table 1 · p. 2
• Figure 2 · p. 2
• Table 2 · p. 2
• Figure 3 · p. 3
• Table 3 · p. 3
• Figure 4 · p. 4
• Table 4 · p. 4
• Table 5 · p. 4
• Table 6 · p. 5
• Table 7 · p. 5
• Figure 5 · p. 5
• Figure 6 · p. 6
• Figure 7 · p. 7
• Table 8 · p. 8
• Figure 8 · p. 9
• Table 9 · p. 9
• Figure 9 · p. 10
• Figure 10 · p. 11
• Figure 11 · p. 14
• Figure 12 · p. 15
• Figure 13 · p. 15
• Figure 14 · p. 16
• Figure 15 · p. 17
• Figure 16 · p. 18

Argument and organization

1. Problem and contribution

   Starts from violations of photometric consistency and distinctive texture cues, explaining why existing diffuse-object benchmarks miss important failures.

2. Argument sequence

   Places material-property observations before dataset construction, then organizes evaluation by matching, SfM, NVS, surfaces and appearance tasks.

3. Evidence and verification

   Tables 1–2 distinguish source shapes, material variants, views and frames, while task-specific evaluation avoids treating all reconstruction problems as one score.

Problem, claim and contribution

Starts from violations of photometric consistency and distinctive texture cues, explaining why existing diffuse-object benchmarks miss important failures.

Introduction and Figure 2, p. 2 · Main paper · Additional source 2

Argument and section order

Places material-property observations before dataset construction, then organizes evaluation by matching, SfM, NVS, surfaces and appearance tasks.

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

Figures, captions and visual explanation

Figure 2 isolates a pose-error artifact on one object; Figure 4 makes material parameters explicit in a parallel-coordinate sweep.

Figures 2 and 4, pp. 2–3 · Main paper · Additional source 2

Tables, comparisons and evidence

Tables 1–2 distinguish source shapes, material variants, views and frames, while task-specific evaluation avoids treating all reconstruction problems as one score.

Tables 1–2, p. 5; Section 5 · Main paper · Additional source 2

Appendix and reproducibility

The supplement connects material properties to violated algorithmic assumptions and records generation annotation formats and access details.

Supplement Appendices A, K and L, pp. 1, 6–9 · Main paper · Additional source 2

Clarity and writing conventions

A material-specific motivation links dataset design to benchmark failures rather than using size alone to justify the resource.

Sections 3–4, pp. 3–6 · Main paper · Additional source 2

What to reuse—and what not to infer

Transferable lesson: For a large synthetic/real dataset, explain what each count means and tie each controlled factor to a scientific failure mode.

Boundary: Shapes, rendered instances and frames are different counting units; the paper uses all three, so do not repeat a single headline number without its denominator.

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

Writing-oriented scan throughout Sections 1–7, PDF pp. 1–8; references pp. 9–12: abstract/framing, section sequence, figure/table captions, evaluation organization and conclusions; not an exhaustive technical verification.

Appendix / supplement

Writing-oriented supplement scan: Supplement Appendices A–N, pp. 1–18: access, composition, matching/reconstruction, material sweeps, physical failure analysis, annotation formats and galleries. Video/code assets were not executed or assessed.

Visually inspected PDF pages

2, 5

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 CVPR 2026 accepted-paper PDF · 12 pages
• Official CVF supplementary PDF · 18 pages