Writing study: Poppy: Polarization-Based Plug-and-Play Guidance for Enhancing Surface Normal Estimation
← ECCV 2026 oral writing corpus
Irene Kim, Sai Tanmay Reddy Chakkera, Alexandros Graikos, Dimitris Samaras, Akshat Dave · Official ECCV 2026 oral record
Figure, table and section ledger
Editorial contribution type: Training, objectives & optimization (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
- ≈ 15.15 page-equivalents
- Main figures / tables
- 10 / 1
- 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.
All detected figure and table locations
Main text
Attached appendix
No recognized caption labels.
Argument and organization
- 1 Introduction; 2 Related Work; 3 Background
Motivates polarization from reflective, textureless and dark cases where RGB priors are unreliable, while explaining why paired polarimetric training data are scarce.
- 4 Method: rendering, guidance parameters and updates
Introduces polarization and normal-to-Stokes conversion before the guidance loss, so the physical observation and learnable offsets are defined before optimization.
- 5 Results; 6 Conclusion
Results separate real from synthetic datasets and test three estimator families; noise and reflectance analyses probe when the physical guidance weakens.
Problem, claim and contribution
Motivates polarization from reflective, textureless and dark cases where RGB priors are unreliable, while explaining why paired polarimetric training data are scarce.
Abstract and Section 1, pp.1–3 · Main paper
Argument and section order
Introduces polarization and normal-to-Stokes conversion before the guidance loss, so the physical observation and learnable offsets are defined before optimization.
Sections 3–4, pp.5–9 · Main paper
Figures, captions and visual explanation
The pipeline distinguishes the frozen estimator from learnable image, normal and radiance offsets. The ablation combines a benchmark matrix with trajectories marking when the normal offset activates.
Figure 3, p.7; Figure 5, p.10 · Main paper
Tables, comparisons and evidence
Results separate real from synthetic datasets and test three estimator families; noise and reflectance analyses probe when the physical guidance weakens.
Table 1, p.9; Figures 8–9, pp.13–14 · Main paper
Appendix and reproducibility
The application discussion points to Supplement Section J for image editing. The separate supplementary PDF was not retrieved, so its organization is not asserted.
Section 5.3, p.14 · Main paper
Clarity and writing conventions
Method prose states which variables change at test time rather than relying on the broad phrase training-free; dataset object counts are given next to the evaluation setup.
Sections 4.2–4.3 and 5.1, pp.8–10 · Main paper
What to reuse—and what not to infer
Transferable lesson: A physics-guided objective needs an observation-to-prediction diagram, explicit frozen/trainable variables, and noise or model-mismatch tests.
Boundary: Training-free does not mean zero test-time optimization or RGB-only input. The event and manuscript use Surface versus Monocular Normal Estimation titles.
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
- 7, 10
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.