Skip to content
Computational Pathology Reading Roadmap

Writing study: RePoseD: Efficient Relative Pose Estimation With Known Depth Information

← ICCV 2025 oral writing corpus

Yaqing Ding, Viktor Kocur, Václav Vávra, Zuzana Berger Haladová, Jian Yang, Torsten Sattler, Zuzana Kukelova · Official ICCV 2025 oral record

Figure, table and section ledger

Editorial contribution type: Theory & formal analysis (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
≈ 8.2 page-equivalents
Main figures / tables
3 / 5
Attached appendix figures / tables
0 / 0
Attached appendix span
No boundary detected; not assumed zero
Before references / appendix: ≈ 74.55%References / intervening material: ≈ 25.45%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 headingStarts on PDF pageEstimated spanShare of entire PDF
1. Introduction1≈ 1.33 pp.12.09%
2. Related Work2≈ 0.67 pp.6.09%
3. Problem Statement3≈ 2.29 pp.20.82%
4. Experiments5≈ 2.73 pp.24.82%
5. Conclusion8≈ 0.8 pp.7.27%
References9≈ 2.8 pp.25.45%
All detected figure and table locations

Main text

Attached appendix

    No recognized caption labels.

    Argument and organization

    1. 1 Introduction; 2 Related Work; 3 Problem Statement

      Asks when monocular depth actually helps and enumerates depth scale/shift and camera-calibration cases.

    2. 3.1 Calibrated Case; 3.2 Focal Length Problems

      Derives compact solvers and contrasts practical overconstrained formulations with expensive minimal systems.

    3. 4 Experiments; 5 Conclusion

      Crosses depth sources, matchers, solvers and robust-estimation choices before conditional recommendations and degeneracies.

    Problem, claim and contribution

    The central question is whether estimated depth improves on point-only geometry, not whether added depth always wins.

    Sections 1–2, physical pp.1–3 · Main paper

    Argument and section order

    A solver taxonomy states correspondences, unknown scales/shifts, degrees of freedom and solution counts before individual algebraic derivations.

    Table 1 and Sections 3.1–3.2, p.4 · Main paper

    Figures, captions and visual explanation

    Speed–accuracy curves fix both matcher and depth source in their captions, while line style distinguishes scoring or estimation frameworks.

    Figures 2–3, p.8 · Main paper

    Tables, comparisons and evidence

    The results retain point-only and depth-based methods, separating hybrid RANSAC from PoseLib and explicitly identifying situations where less accurate depth favors the five-point solver.

    Tables 3–5 and Sections 4.1–4.3, pp.6–8 · Main paper

    Appendix and reproducibility

    Additional depth models, datasets, scoring/local-optimization strategies and solver cases are routed to supplemental material, not inspected.

    Sections 3–4, pp.3–7 · Main paper

    Clarity and writing conventions

    The limitations acknowledge depth-estimation cost separately from solver runtime and list coplanar/pure-translation focal degeneracies.

    Limitations, pp.7–8 · Main paper

    What to reuse—and what not to infer

    Transferable lesson: For a family of geometric solvers, organize assumptions in a taxonomy and make performance recommendations conditional on measurement quality.

    Boundary: A solver-only timing advantage excludes feature matching and depth prediction. Results depend on depth accuracy, camera assumptions and robust-estimation framework; a lower correspondence count does not remove geometric degeneracy. Algebraic correctness was not independently verified.

    Apply this lesson using the argument and evidence worksheet.

    Inspection record and sources

    Checked
    2026-10-07
    Reading status
    Writing-focused manuscript scan + selected visuals inspected
    Main text
    Writing-oriented scan across the main manuscript, physical PDF pp.1–8, covering framing, section progression, method explanations, captions, comparison protocols and concluding scope; reference boundary checked. Selected full-page rasters were inspected. Not exhaustive line-by-line reading, proof verification or experimental reproduction.
    Appendix / supplement
    Main-paper appendix/supplement references were checked. A separate supplementary source is linked in the inventory but was not retrieved or inspected; its contents are not included in the reading or visual-page counts.
    Visually inspected PDF pages
    4, 8

    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.