Writing study: PhyGaP: Physically-Grounded Gaussians with Polarization Cues

CVPR overviewCorpus atlasBy contribution typeVisual galleryRules & templateWriting patternsPaper studies

← CVPR 2026 oral writing corpus

Jiale Wu, Xiaoyang Bai, Zongqi He, Weiwei Xu, YIFAN PENG · 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: 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

11 physical pages

Before references / appendix

≈ 8.11 page-equivalents

Main figures / tables

9 / 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	≈ 0.73 pp.	6.64%
2. Related Work	2	≈ 0.76 pp.	6.91%
3. Preliminaries: Ref-Gaussian	3	≈ 0.86 pp.	7.82%
4. Method	4	≈ 1.65 pp.	15%
5. Experiments	5	≈ 2.39 pp.	21.73%
6. Conclusion	8	≈ 0.85 pp.	7.73%
References	9	≈ 2.89 pp.	26.27%

All detected figure and table locations

Main text

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

Located appendix only: starts on physical p.1; ≈ 6.94 page-equivalents, 7 figure labels and 3 table labels. This interval is distinct from the whole file.

Detected heading	PDF page	Estimated span
Supplementary Material	1	≈ 0.02 pp.
1. 3D Gaussian Splatting (3DGS) Preliminaries	1	≈ 0.27 pp.
2. Detailed Formulation of PolarDR	1	≈ 1.91 pp.
3. Training Details	3	≈ 0.65 pp.
4. Additional Results	3	≈ 2.43 pp.
5. Supplementary Video	6	≈ 0.03 pp.
References	6	≈ 1.64 pp.

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

Argument and organization

1. Problem and contribution

   The goal is physically meaningful decomposition and relighting, not simply memorizing glossy appearance for novel-view synthesis. The introduction motivates polarization as information that helps separate geometry, material and illumination.

2. Argument sequence

   Ref-Gaussian and deferred-rendering preliminaries introduce the inherited representation before PolarDR, GridMap and training explain the intervention. Evaluation separates reconstruction, relighting and analysis rather than blending all outputs into one gallery.

3. Evidence and verification

   Table 1 puts novel-view PSNR and normal cosine distance in separate column families; real and synthetic datasets are identified in the text. The table footnote warns that some baselines include test viewpoints in training, preserving an important comparison qualification.

Problem, claim and contribution

The goal is physically meaningful decomposition and relighting, not simply memorizing glossy appearance for novel-view synthesis. The introduction motivates polarization as information that helps separate geometry, material and illumination.

Introduction; Sections 3–4 · Main paper · Additional source 2

Argument and section order

Ref-Gaussian and deferred-rendering preliminaries introduce the inherited representation before PolarDR, GridMap and training explain the intervention. Evaluation separates reconstruction, relighting and analysis rather than blending all outputs into one gallery.

Sections 3–5 · Main paper · Additional source 2

Figures, captions and visual explanation

Figure 2 maps roughness, index of refraction, normal and albedo through diffuse/specular polarized rendering, and places global/local environment maps next to the GridMap branch. The loss arrows identify the observations constraining each output.

Figure 2, PDF p.3 · Main paper · Additional source 2

Tables, comparisons and evidence

Table 1 puts novel-view PSNR and normal cosine distance in separate column families; real and synthetic datasets are identified in the text. The table footnote warns that some baselines include test viewpoints in training, preserving an important comparison qualification.

Table 1 and footnote, PDF p.6 · Main paper · Additional source 2

Appendix and reproducibility

The supplement elaborates the reflectance model and training/capture setup, adds geometry and image metrics, examines partial polarization cues and includes failure discussion. Derivations support the physical claims while extra scenes test their range.

Supplementary PDF pp.1–7 · Main paper · Additional source 2

Clarity and writing conventions

Qualitative decomposition marks unavailable baseline components as N/A rather than displaying a misleading blank as failure. Relighting panels identify the imposed illumination, giving the visual comparison a physical interpretation.

Figures 5–8, main PDF pp.7–8 · Main paper · Additional source 2

What to reuse—and what not to infer

Transferable lesson: In inverse rendering, align diagram branches, measured signals and decomposed outputs; use captions to state real/synthetic status and unavailable quantities.

Boundary: Novel-view image quality, accurate material decomposition and controllable relighting are different claims. Also preserve the published warning about unequal training-view access.

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 main PDF pp.1–8 and references pp.9–11: abstract/framing, section sequence, figure/table captions, evaluation organization and conclusions; not an exhaustive technical verification.

Appendix / supplement

Writing-oriented supplement scan: all seven supplementary PDF pages, including polarized reflectance derivations, training/setup, additional metrics, ablations and failures. Video/code assets were not executed or 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 CVF open-access CVPR 2026 accepted-paper PDF · 11 pages
• Official CVF supplementary ZIP member PDF; see URL fragment for member · 7 pages