Writing study: PRISM-VO: Scale-Aware Visual Odometry Using Photometric Plenoptic Bundle Adjustment
← ECCV 2026 oral writing corpus
Aymeric Fleith, Julian Zirbel, Daniel Cremers, Niclas Zeller · 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
- 18 physical pages
- Before references / appendix
- ≈ 15.15 page-equivalents
- Main figures / tables
- 12 / 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. Figure 6a and 6b are panel references inside Figure 6 caption, not independently numbered figures.
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 | ≈ 1.14 pp. | 6.33% |
| 2 Related Work | 2 | ≈ 1.79 pp. | 9.94% |
| 3 Preliminaries | 4 | ≈ 1.04 pp. | 5.78% |
| 4 PRISM-VO: Plenoptic Direct Visual Odometry | 5 | ≈ 4.89 pp. | 27.17% |
| 5 Evaluation | 10 | ≈ 5.07 pp. | 28.17% |
| 6 Conclusion | 15 | ≈ 0.21 pp. | 1.17% |
| Acknowledgements | 15 | ≈ 0.36 pp. | 2% |
| References | 16 | ≈ 2.85 pp. | 15.83% |
All detected figure and table locations
Main text
Attached appendix
No recognized caption labels.
Argument and organization
- 1 Introduction; 2 Related Work; 3 Preliminaries
Treats metric scale and plenoptic observations as the central design issue, rather than presenting another generic monocular odometry benchmark improvement.
- 4 PRISM-VO: Plenoptic Direct Visual Odometry
Camera geometry and notation precede the front-end/back-end overview, point selection and optimization; evaluation then separates drift from pose-estimation error.
- 5 Evaluation; 6 Conclusion
The paper states precision thresholds, separates plenoptic-specific comparisons and repeats non-deterministic pipelines ten times per sequence before plotting aggregate distributions.
Problem, claim and contribution
Treats metric scale and plenoptic observations as the central design issue, rather than presenting another generic monocular odometry benchmark improvement.
Abstract and Section 1, pp.1–2 · Main paper
Argument and section order
Camera geometry and notation precede the front-end/back-end overview, point selection and optimization; evaluation then separates drift from pose-estimation error.
Sections 3–5, pp.4–14 · Main paper
Figures, captions and visual explanation
The pipeline uses explicit tracking and optimization compartments, decision diamonds and distinct photometric/depth information arrows. Cumulative error plots retain distribution-level behavior.
Figure 4, p.6; Figure 11, p.13 · Main paper
Tables, comparisons and evidence
The paper states precision thresholds, separates plenoptic-specific comparisons and repeats non-deterministic pipelines ten times per sequence before plotting aggregate distributions.
Table 1 and Section 5.2, p.13 · Main paper
Appendix and reproducibility
Projection details and complete Jacobian derivation are delegated to supplementary material while the residual definitions remain in the main text; the supplement was not retrieved.
Sections 3.1 and 4.4, pp.5,8–9 · Main paper
Clarity and writing conventions
The method opens with a section roadmap that mirrors the pipeline figure, and evaluation headings name the quantity tested rather than only the dataset.
Section 4, p.5; Sections 5.2–5.4, pp.11–14 · Main paper
What to reuse—and what not to infer
Transferable lesson: For a stateful geometry system, use a front-end/back-end flowchart plus residual definitions and error distributions; explain calibration and initialization explicitly.
Boundary: Comparisons depend on sensor type, synthesized focused images and scale-alignment protocols. A visual trajectory alone does not establish metric accuracy.
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
- 6, 13
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.