Skip to content
Computational Pathology Reading Roadmap

Writing study: Teeth Reconstruction and Performance Capture Using a Phone Camera

← ICCV 2025 oral writing corpus

Weixi Zheng, Jingwang Ling, Zhibo Wang, Quan Wang, Feng Xu · Official ICCV 2025 oral record

Figure, table and section ledger

Editorial contribution type: Domain-grounded methods & physical 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
11 physical pages
Before references / appendix
≈ 8.12 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: ≈ 73.82%References / intervening material: ≈ 26.18%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≈ 1.37 pp.12.45%
2. Related Work2≈ 0.63 pp.5.73%
3. Preliminaries3≈ 0.38 pp.3.45%
4. Method3≈ 1.99 pp.18.09%
5. Experiments5≈ 2.95 pp.26.82%
6. Limitation8≈ 0.14 pp.1.27%
7. Conclusion8≈ 0.18 pp.1.64%
Acknowledgments9≈ 0.08 pp.0.73%
References9≈ 2.88 pp.26.18%
All detected figure and table locations

Main text

Attached appendix

    No recognized caption labels.

    Argument and organization

    1. 1 Introduction; 2 Related Work; 3 Preliminaries

      Motivates explicit teeth as a missing controllable facial component and defines inherited face/dental priors.

    2. 4 Method

      Combines mesh/SDF representations and jaw rigging, then introduces semantic matching, contact and occlusion-aware fitting.

    3. 5 Experiments; 6 Limitation; 7 Conclusion

      Separates two-stage phone capture, synthetic geometry evaluation, reconstruction/tracking comparisons and component-specific failures.

    Problem, claim and contribution

    The accessible device claim is paired with a specific acquisition protocol rather than implying arbitrary casual video reconstructs all dental anatomy.

    Sections 1 and 5, physical pp.1–2,5 · Main paper

    Argument and section order

    Representation adaptation and anatomical rigging precede losses, explaining why meshes serve rendering while SDFs serve collision tests.

    Sections 4.1–4.2, pp.3–5 · Main paper

    Figures, captions and visual explanation

    The overview places mesh and SDF roles on separate branches, and later ablations pair visible teeth/lip failures with the removed loss or occlusion strategy.

    Figure 2, p.4; Figures 5–7, p.8 · Main paper

    Tables, comparisons and evidence

    The main comparison separates performance capture from static shape reconstruction; geometry error is evaluated on synthetic visible-teeth regions, while mask overlap checks alignment over frames.

    Table 1 and Table 2, p.8; Sections 5.2–5.4, pp.6–8 · Main paper

    Appendix and reproducibility

    The paper repeatedly directs temporal performance and additional results to a supplementary video, which was not viewed; static page inspection does not establish temporal stability.

    Sections 5 and 5.2, pp.5–6 · Main paper

    Clarity and writing conventions

    The preprocessing explicitly describes manual per-tooth clicks for SAM2 propagation and the limitation returns to dependence on segmentation quality.

    Section 5, p.6; Section 6, p.8 · Main paper

    What to reuse—and what not to infer

    Transferable lesson: For accessible capture systems, disclose user interaction, calibration and optimization time, and separate synthetic geometric truth from real qualitative demonstrations.

    Boundary: Four phone-captured participants and synthetic visible-teeth metrics do not establish clinical dental reconstruction accuracy. The pipeline uses learned dental/face priors, manual segmentation and lengthy optimization; smartphone input alone does not mean fully automatic or real-time processing.

    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.