Writing study: Relightable Holoported Characters: Capturing and Relighting Dynamic Human Performance from Sparse Views

CVPR overviewCorpus atlasBy contribution typeVisual galleryRules & templateWriting patternsPaper studies

← CVPR 2026 oral writing corpus

Kunwar Maheep Singh, Jianchun Chen, Vladislav Golyanik, Stephan Garbin, Thabo Beeler, Rishabh Dabral, Marc Habermann, Christian Theobalt · 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

≈ 8.08 page-equivalents

Main figures / tables

7 / 2

Attached appendix figures / tables

0 / 0

Attached appendix span

Separate file recorded below; not in this PDF total

Before references / appendix: ≈ 73.45%References / intervening material: ≈ 26.55%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.

Source-bound correction: Figure 3 is raster-visible on physical page 4: a full-width architecture diagram with a caption beneath it. The caption is absent from text extraction; added after visual inspection, using a render-estimated position.

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	≈ 1.24 pp.	11.27%
2. Related Work	2	≈ 0.8 pp.	7.27%
3. Dataset and Capture Strategy	3	≈ 0.38 pp.	3.45%
4. Method	3	≈ 2.97 pp.	27%
5. Experiments	6	≈ 1.97 pp.	17.91%
6. Limitations and Future Work	8	≈ 0.15 pp.	1.36%
7. Conclusion	8	≈ 0.19 pp.	1.73%
8. Acknowledgements	9	≈ 0.04 pp.	0.36%
References	9	≈ 2.92 pp.	26.55%

All detected figure and table locations

Main text

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

Located appendix only: starts on physical p.1; ≈ 8.7 page-equivalents, 10 figure labels and 5 table labels. This interval is distinct from the whole file.

Detected heading	PDF page	Estimated span
1. Overview	1	≈ 0.28 pp.
2. Character Animation Model	1	≈ 0 pp.
3. Diffuse Shading	1	≈ 0.27 pp.
4. Cross-attention Mechanism	1	≈ 0.32 pp.
5. Gaussian Projection and Rendering	2	≈ 0.17 pp.
6. RelightNet	2	≈ 0.55 pp.
7. Training Details	2	≈ 0.97 pp.
8. Additional Data Capture Details	3	≈ 0.4 pp.
9. Baseline Implementation Details	4	≈ 0.52 pp.
10. Dynamic OLAT Experiment	4	≈ 0.5 pp.
11. Runtime and Memory	5	≈ 0.1 pp.
12. Further Ablations	5	≈ 0.96 pp.
13. Additional Qualitative Results	6	≈ 2.71 pp.
References	9	≈ 0.95 pp.

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

Read-only audit 2026-09-26: restored actual supplementary section headings from cached PDF layout, excluding table-of-contents entries and retaining physical PDF page coordinates. This measures reading-order spans, not occupied text area.

Argument and organization

1. 3. Data Capture and 4. Method

   Explains the acquisition conditions before the animation/features/relighting stages.

2. 5. Experiments and 6. Limitations

   Compares adapted baselines and tests feature/capture choices, then limits identity and material scope.

Problem, claim and contribution

The paper contrasts expensive lighting capture with sparse-view inference; four cameras at inference are distinguished from multi-view lightstage training.

pp. 1–3 · Main paper · Additional source 2

Argument and section order

The method is split into animation, physics-informed features, and RelightNet, and those subsections are repeated inside the architecture figure.

§§4.1–4.3; Figure 3 · Main paper · Additional source 2

Figures, captions and visual explanation

The wide architecture panel uses input thumbnails, UV feature stacks, an attention inset, and a rendered output, linking physical inputs to learned components.

Figure 3 p. 4 · Main paper · Additional source 2

Tables, comparisons and evidence

The comparison table separates subjects and metrics; its caption explains ground-truth environment-map modifications to competing methods instead of silently equating tasks.

Table 1 p. 7 · Main paper · Additional source 2

Appendix and reproducibility

The supplement reports runtime by component and tests lighting diversity and cross-identity adaptation, including material/UV bias artifacts rather than suggesting unrestricted transfer.

Supplement §§11–13; Tables 2–5 and Figure 8 · Main paper · Additional source 2

Clarity and writing conventions

A dedicated limitations section states per-identity training and failures under topology changes, translucent materials, and some specular detail.

§6 p. 8 · Main paper · Additional source 2

What to reuse—and what not to infer

Transferable lesson: Explain mismatched baseline input privileges in the table caption, and synchronize architecture labels with subsection names.

Boundary: Photorealistic examples do not establish cross-identity or unrestricted lighting generalization; this is a person-specific system.

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 the nine-page official ZIP-member PDF for feature/attention/architecture details, training/capture and baseline settings, runtime/memory breakdown, lighting diversity, few-shot adaptation failures, and extra relighting comparisons; videos were not viewed.

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 supplementary PDF extracted from CVF ZIP archive member; retrieved 2026-09-26 · 9 pages