Writing study: Heat Kernel Textures -- the Geodesic Gaussians That Do Not Splat
← ECCV 2026 oral writing corpus
Simone Foti, Caner Korkmaz, Stefanos Zafeiriou, Tolga Birdal · Official ECCV 2026 oral record
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
- 19 physical pages
- Before references / appendix
- ≈ 14.69 page-equivalents
- Main figures / tables
- 4 / 2
- Attached appendix figures / tables
- 0 / 0
- Attached appendix span
- No boundary detected; not assumed zero
Extraction notes: No attached appendix boundary detected. Zero means no recognized caption, not independently verified absence.
Source-bound correction: All top-level main headings and the reference boundary checked against source PDF text; source-bound positions use physical single-column y/page-height, not a two-column reading-order surrogate. Running page-number/author titles, affiliations, numbered contribution bullets, footnotes and bibliography continuations are excluded. This linked manuscript contains no appended supplementary section; separate supplement links were not scanned. Selected disputed heading locations also checked in rendered source pages.
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 | ≈ 1.47 pp. | 7.74% |
| 2 Related Work | 3 | ≈ 0.95 pp. | 5% |
| 3 Background & Notation | 4 | ≈ 1.23 pp. | 6.47% |
| 4 Heat Kernel Textures | 5 | ≈ 5.03 pp. | 26.47% |
| 5 Experiments | 10 | ≈ 4.33 pp. | 22.79% |
| 6 Conclusion | 14 | ≈ 0.84 pp. | 4.42% |
| Acknowledgements | 15 | ≈ 0.12 pp. | 0.63% |
| References | 15 | ≈ 4.31 pp. | 22.68% |
All detected figure and table locations
Main text
Attached appendix
No recognized caption labels.
Argument and organization
- 1 Introduction; 2 Related Work; 3 Background and Notation
Defines seams, distortion and storage waste as limitations of UV mapping, then proposes an intrinsic representation rather than another image-space texture network.
- 4 Heat Kernel Textures: spectral interpolation, spatial evaluation, optimization and rendering
Introduces manifold and spectral notation before kernel parameters, interpolation and optimization; evaluation separates fitting existing textures from multi-view observations.
- 5 Experiments; 6 Conclusion
The main table includes quality, rendering time and storage with units and uncertainty, making slower rendering visible alongside favorable storage and visual quality.
Problem, claim and contribution
Defines seams, distortion and storage waste as limitations of UV mapping, then proposes an intrinsic representation rather than another image-space texture network.
Abstract and Section 1, pp.1–2 · Main paper
Argument and section order
Introduces manifold and spectral notation before kernel parameters, interpolation and optimization; evaluation separates fitting existing textures from multi-view observations.
Sections 3–5, pp.4–13 · Main paper
Figures, captions and visual explanation
The qualitative grid repeats the same objects and viewpoints across methods and states storage comparability; albedo-only rendering isolates the texture representation.
Figure 2, p.12 · Main paper
Tables, comparisons and evidence
The main table includes quality, rendering time and storage with units and uncertainty, making slower rendering visible alongside favorable storage and visual quality.
Table 1, p.14 · Main paper
Appendix and reproducibility
Spectral ringing, mass approximations, sampling and exact hyperparameters are delegated to supplementary material; those separate derivations were not inspected.
Sections 4–5.2, pp.6,8,11 · Main paper
Clarity and writing conventions
Implementation and metrics precede comparison, and the limitations narrow the present experiments to albedo rather than all material attributes.
Sections 5.2–5.3, pp.10–11; Limitations, p.15 · Main paper
What to reuse—and what not to infer
Transferable lesson: A representation paper needs a controlled visual grid and a multi-axis quality/storage/runtime table, with the represented physical quantity clearly delimited.
Boundary: Lower storage does not imply faster rendering. The current results concern the reported curated meshes and primarily albedo textures.
Apply this lesson using the argument and evidence worksheet.
Inspection record and sources
- Checked
- 2026-10-02
- Reading status
- Writing-focused manuscript scan + selected visuals inspected
- Main text
- Writing-oriented scan across the manuscript main argument, physical PDF pp.1–15: framing and section roadmaps, method/argument explanations, figure and table captions, comparison protocols, conclusions and limitations. Selected full-page rasters were inspected. This is not exhaustive line-by-line technical reading, proof verification or experimental reproduction.
- Appendix / supplement
- Main-manuscript pointers to appendix/supplement and the reference boundary were checked. Separate supplementary PDFs were not retrieved or inspected; their contents are not included in inspected-page counts.
- Visually inspected PDF pages
- 12, 14
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.