Writing study: Event-based Visual Vibrometry

ICCV overviewCorpus atlasBy contribution typeVisual galleryRules & templateWriting patternsPaper studies

← ICCV 2025 oral writing corpus

Xinyu Zhou, Peiqi Duan, Yeliduosi Xiaokaiti, Chao Xu, Boxin Shi · Official ICCV 2025 oral record

Observed writing choices, not acceptance rules. This study examines the inspected manuscript version. It does not establish why the paper was accepted or that its presentation choices should be copied unchanged.

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

≈ 8.05 page-equivalents

Main figures / tables

6 / 3

Attached appendix figures / tables

0 / 0

Attached appendix span

No boundary detected; not assumed zero

Before references / appendix: ≈ 73.18%References / intervening material: ≈ 26.82%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 heading	Starts on PDF page	Estimated span	Share of entire PDF
1. Introduction	1	≈ 0.98 pp.	8.91%
2. Related Works	2	≈ 0.58 pp.	5.27%
3. Method	3	≈ 2.99 pp.	27.18%
4. Experiments	6	≈ 2.41 pp.	21.91%
5. Conclusion	8	≈ 0.13 pp.	1.18%
Acknowledgement	8	≈ 0.19 pp.	1.73%
References	9	≈ 2.95 pp.	26.82%

All detected figure and table locations

Main text

• Figure 1 · p. 1
• Figure 2 · p. 4
• Figure 3 · p. 5
• Table 1 · p. 6
• Figure 4 · p. 7
• Table 2 · p. 7
• Figure 5 · p. 7
• Figure 6 · p. 8
• Table 3 · p. 8

Attached appendix

No recognized caption labels.

Argument and organization

1. 1 Introduction; 2 Related Works

   Motivates dense high-frequency vibration measurement under bandwidth and illumination constraints.

2. 3 Method

   Derives event-based coarse motion, then learns refinement and temporal accumulation from synthetic supervision.

3. 4 Experiments; 5 Conclusion

   Progresses from synthetic flow accuracy to real audio and material demonstrations, then ablates components and states the simulation gap.

Problem, claim and contribution

The sensing proposal combines a reference RGB frame with event streams; it is neither event-only nor a conventional high-speed video method.

Figure 1 and introduction, physical pp.1–2 · Main paper

Argument and section order

The coarse estimator’s sparsity, quantization and noise limitations explicitly motivate the learned refinement module.

Sections 3.2–3.3, p.4 · Main paper

Figures, captions and visual explanation

The network diagram separates short-interval motion refinement from accumulated displacement; real experiments pair physical setups with reference and recovered spectrograms.

Figure 3, p.5; Figures 4–5, p.7 · Main paper

Tables, comparisons and evidence

The rod experiment specifies three materials, two clamped lengths and three illumination levels, comparing modulus estimates to manufacturer values rather than direct mechanical retesting.

Section 4.3 and Table 2, p.7 · Main paper

Appendix and reproducibility

The main paper itself carries synthetic-data construction, training settings, component ablations and the explicit simulation-to-real limitation; no detailed supplement claim is needed to explain that evidence chain.

Section 3.4, pp.5–6; Section 4.4 and limitations, p.8 · Main paper

Clarity and writing conventions

The heterogeneous-material example acknowledges imperfect reconstruction alignment from damping even though the two cubes can be distinguished.

Section 4.3, p.8 · Main paper

What to reuse—and what not to infer

Transferable lesson: For a sensing pipeline, separately validate the estimated intermediate signal and the downstream physical inference, naming the provenance of each reference measurement.

Boundary: The small controlled audio/rod/cube demonstrations do not establish general-purpose defect detection or calibrated material tomography. Modulus errors are signed percentages despite a downward arrow, so absolute proximity to zero matters. The bandwidth comparison is against compressed 1000-fps video at 720p, not total inference runtime or every acquisition condition.

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

5, 7

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.

• Official CVF open-access ICCV 2025 accepted-paper PDF, retrieved 7 October 2026; CVF states identical to accepted version except watermark; not assumed identical to initial submission · 11 pages