Writing study: RS-vHeat: Heat Conduction Guided Efficient Remote Sensing Foundation Model

ICCV overviewCorpus atlasBy contribution typeVisual galleryRules & templateWriting patternsPaper studies

← ICCV 2025 oral writing corpus

Huiyang Hu, Peijin Wang, Hanbo Bi, Boyuan Tong, Zhaozhi Wang, Wenhui Diao, Hao Chang, Yingchao Feng, Ziqi Zhang, Yaowei Wang, Qixiang Ye, Kun Fu, Xian Sun · 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: 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

12 physical pages

Before references / appendix

≈ 8.1 page-equivalents

Main figures / tables

5 / 9

Attached appendix figures / tables

0 / 0

Attached appendix span

No boundary detected; not assumed zero

Before references / appendix: ≈ 67.5%References / intervening material: ≈ 32.5%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	≈ 1.31 pp.	10.92%
2. Related Work	2	≈ 1.04 pp.	8.67%
3. Proposed RS-vHeat	3	≈ 1.89 pp.	15.75%
4. Experiments	5	≈ 3.18 pp.	26.5%
5. Conclusion	8	≈ 0.23 pp.	1.92%
6. Acknowledgment	9	≈ 0.06 pp.	0.5%
References	9	≈ 3.9 pp.	32.5%

All detected figure and table locations

Main text

• Figure 1 · p. 1
• Figure 2 · p. 3
• Figure 3 · p. 4
• Figure 4 · p. 5
• Table 1 · p. 6
• Table 2 · p. 6
• Table 3 · p. 6
• Table 4 · p. 7
• Table 5 · p. 7
• Table 6 · p. 7
• Table 7 · p. 7
• Table 8 · p. 8
• Table 9 · p. 8
• Figure 5 · p. 8

Attached appendix

No recognized caption labels.

Argument and organization

1. 1 Introduction; 2 Related Work

   Pairs global receptive-field cost with the wish for a physically motivated visual operator.

2. 3 Proposed RS-vHeat

   Separates frequency masking, heat-inspired encoding and multi-domain reconstruction/contrastive objectives.

3. 4 Experiments; 5 Conclusion

   Measures resolution-dependent resources before four downstream task families and component/loss controls.

Problem, claim and contribution

Motivates the operator through the conflict between global dependencies and high-resolution remote-sensing costs, with small-object masking as a second design issue.

Sections 1 and 3, physical pp.1–4 · Main paper

Argument and section order

The method moves from frequency-domain input construction to an encoder and then to the losses, while downstream heads and modalities are explained task by task.

Sections 3 and 4.2, pp.3–7 · Main paper

Figures, captions and visual explanation

A high-level pretraining strip is expanded into modality/frequency branches and a repeated-stage inset; labels separate paired from unpaired optical/SAR data.

Figure 2, p.3 · Main paper

Tables, comparisons and evidence

Resolution curves report throughput, GPU memory and FLOPs separately with one A100 80GB and batch size 32 in the caption; downstream tables group backbone families instead of implying identical pretraining.

Figure 4, p.5; Tables 1 and 4, pp.6–7 · Main paper

Appendix and reproducibility

The prior vHeat design, masking details, dataset descriptions and qualitative outputs are deferred to supplementary material; only main pointers were checked.

Sections 2–4, pp.2–4,6 · Main paper

Clarity and writing conventions

The results openly acknowledge lower accuracy than the much larger SkySense on some segmentation settings, retaining a quality/resource tradeoff.

Section 4.2, p.6 · Main paper

What to reuse—and what not to infer

Transferable lesson: For a physically inspired architecture, connect each analogy to an explicit computation and evaluate its resource advantage across input resolutions.

Boundary: The learned thermal space is not a measured temperature field; physical inspiration alone does not validate interpretability. Resource curves use a fixed batch/hardware contract and do not equal deployment latency for every downstream head.

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

3, 5

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 · 12 pages