Skip to content
Computational Pathology Reading Roadmap

Writing study: Forecasting Continuous Non-Conservative Dynamical Systems in SO(3)

← ICCV 2025 oral writing corpus

Lennart Bastian, Mohammad Rashed, Nassir Navab, Tolga Birdal · Official ICCV 2025 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
11 physical pages
Before references / appendix
≈ 8.15 page-equivalents
Main figures / tables
5 / 3
Attached appendix figures / tables
0 / 0
Attached appendix span
No boundary detected; not assumed zero
Before references / appendix: ≈ 74.09%References / intervening material: ≈ 25.91%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≈ 0.93 pp.8.45%
2. Related Works2≈ 0.87 pp.7.91%
3. Preliminaries3≈ 0.23 pp.2.09%
4. SO(3) Savitzky-Golay Neural-CDEs3≈ 2.45 pp.22.27%
5. Emperical Evaluation5≈ 2.92 pp.26.55%
6. Conclusion8≈ 0.4 pp.3.64%
References9≈ 2.85 pp.25.91%
All detected figure and table locations

Main text

Attached appendix

    No recognized caption labels.

    Argument and organization

    1. 1 Introduction; 2 Related Works; 3 Preliminaries

      Separates unknown physical parameters, non-conservative forces and noisy rotational observations.

    2. 4 SO(3) Savitzky-Golay Neural-CDEs

      Defines manifold control paths and filtering assumptions before weighted regression, second-order dynamics and training.

    3. 5 Empirical Evaluation; 6 Conclusion

      Tests simulated torque regimes and real trajectories, then separates component accuracy, solver evaluations and runtime.

    Problem, claim and contribution

    The paper distinguishes learning dynamics from estimating object pose, allowing simulated dynamics training to be coupled with a separately trained pose detector.

    Sections 2 and 5.1, physical pp.3,7 · Main paper

    Argument and section order

    Definitions and the control-path theorem state the rotational-window assumption before the model is evaluated; the treatment includes a proof sketch rather than hiding all theory in supplements.

    Sections 4.1–4.5, pp.3–5 · Main paper

    Figures, captions and visual explanation

    The overview visually separates noisy observations, manifold filtering, latent integration and future rotations; trajectory plots distinguish observed inputs from forecast curves.

    Figure 2, p.4; Figure 4, p.8 · Main paper

    Tables, comparisons and evidence

    The ablation reports rotational error and milliseconds alongside a separate number-of-function-evaluations plot; fewer evaluations are not silently equated to proportional wall-clock savings.

    Table 3 and Figure 5, p.8 · Main paper

    Appendix and reproducibility

    Matrix construction, baseline details and pose-estimator comparisons are routed to Appendices C.2, B.2 and A.1 respectively; those were not inspected.

    Sections 4.2 and 5, pp.4,6–7 · Main paper

    Clarity and writing conventions

    The real-data visualization caption explicitly supplies ground-truth translation, and the conclusion limits the method to SO(3), not coupled SE(3) motion.

    Figure 3, p.7; limitations, p.8 · Main paper

    What to reuse—and what not to infer

    Transferable lesson: Keep input-state estimation, dynamics forecasting and visualization-only privileged quantities explicit, and pair solver-complexity metrics with runtime.

    Boundary: The bounded rotational window avoids the logarithm discontinuity; it is a condition, not a universal smoothness guarantee. Forecasting results at the reported short horizons do not establish arbitrary long-term stability or full 6D tracking; theorem arguments were scanned, not proof-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.