Skip to content
Computational Pathology Reading Roadmap

Writing study: NURBS Splatting: A Unified Differentiable Rendering Framework for Vector Graphics

← ECCV 2026 oral writing corpus

Jingye Qiu, Shizhe Zhou · Official ECCV 2026 oral record

Figure, table and section ledger

Editorial contribution type: Efficiency, inference & systems (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
≈ 14.15 page-equivalents
Main figures / tables
7 / 2
Attached appendix figures / tables
0 / 0
Attached appendix span
No boundary detected; not assumed zero
Before references / appendix: ≈ 78.61%References / intervening material: ≈ 21.39%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.

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.

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≈ 1.15 pp.6.39%
2 Related Work2≈ 1.47 pp.8.17%
3 Method4≈ 3.62 pp.20.11%
4 Applications7≈ 2.79 pp.15.5%
5 Experiments10≈ 3.83 pp.21.28%
6 Conclusion14≈ 0.35 pp.1.94%
Acknowledgements14≈ 0.42 pp.2.33%
References15≈ 3.85 pp.21.39%
All detected figure and table locations

Main text

Attached appendix

    No recognized caption labels.

    Argument and organization

    1. 1 Introduction; 2 Related Work

      Motivates rational splines from CAD and vector-editing requirements and identifies the restricted primitives of existing differentiable renderers.

    2. 3 Method; 4 Applications

      Defines primitives, contour/region sampling, rasterization and optimization before three applications, keeping the reusable renderer separate from task-specific losses.

    3. 5 Experiments; 6 Conclusion

      The vectorization table reports both quality and time, and an ablation without annealing has stronger quality but slower runtime than the full method.

    Problem, claim and contribution

    Motivates rational splines from CAD and vector-editing requirements and identifies the restricted primitives of existing differentiable renderers.

    Abstract and Section 1, pp.1–2 · Main paper

    Argument and section order

    Defines primitives, contour/region sampling, rasterization and optimization before three applications, keeping the reusable renderer separate from task-specific losses.

    Sections 3–5, pp.4–13 · Main paper

    Figures, captions and visual explanation

    The overview tracks control points, rational weights and knots into sampled primitives and back through gradients; the representation's editable parameters remain visible.

    Figure 1, p.2 · Main paper

    Tables, comparisons and evidence

    The vectorization table reports both quality and time, and an ablation without annealing has stronger quality but slower runtime than the full method.

    Table 2 and Section 5.3, p.13 · Main paper

    Appendix and reproducibility

    SDF implementation, diagnostic primitive tests and editability visualizations are pointed to in supplementary material, which was not retrieved as a separate inspected source.

    Sections 3.3 and 5.1, pp.6,10–11 · Main paper

    Clarity and writing conventions

    The efficiency discussion concedes that advantages do not hold for all simple primitives, and dataset replacement is explained rather than silently assumed comparable.

    Section 5.1, p.10; Section 5.3, p.13 · Main paper

    What to reuse—and what not to infer

    Transferable lesson: For differentiable renderers, show the parameter-to-pixel-to-gradient path and report the quality/time trade-off of individual accelerations.

    Boundary: Faster is conditional on primitive and application settings; the full configuration is not uniformly best in every quality column.

    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.1–14: 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
    2, 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.