Writing study: Learning Diffeomorphism for Medical Image Registration with Time-Embedded Architectures Using Semigroup Regularization

CVPR overviewCorpus atlasBy contribution typeVisual galleryRules & templateWriting patternsPaper studies

← CVPR 2026 oral writing corpus

Mohammadjavad Matinkia, Nilanjan Ray · Official CVPR 2026 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: Training, objectives & optimization (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

≈ 8.1 page-equivalents

Main figures / tables

8 / 7

Attached appendix figures / tables

0 / 0

Attached appendix span

Separate file recorded below; not in this PDF total

Before references / appendix: ≈ 73.64%References / intervening material: ≈ 26.36%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: Raster inspection confirms Figure 3 on physical page 3 (right-column OASIS registration comparison), whose caption is absent from extracted text. Its position is render-estimated. Table 4 on page 7 has a separately extracted label; its source coordinate is retained. Main Figure 7 and Figure 8 on page 8 are also counted.

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	≈ 1.47 pp.	13.36%
2. Related Works	2	≈ 0.44 pp.	4%
3. Background	3	≈ 1.02 pp.	9.27%
4. Proposed Method	4	≈ 1.06 pp.	9.64%
5. Experiments	5	≈ 3.43 pp.	31.18%
6. Conclusion	8	≈ 0.26 pp.	2.36%
Acknowledgments	9	≈ 0.05 pp.	0.45%
References	9	≈ 2.9 pp.	26.36%

All detected figure and table locations

Main text

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

Attached appendix

No recognized caption labels.

Separate source files—excluded from canonical-PDF totals

A separate author version may repeat main text and references. Whole-file lengths and counts are not extra appendix material and are never added to the canonical PDF totals. Read the study's source scope for which sections received substantive reading versus layout inspection.

Additional source 1

Separate PDF (or ZIP containing it): whole-file layout of 10 physical pages; 8 detected figures and 7 tables. These may include overlapping main-text material.

Located appendix only: starts on physical p.1; ≈ 9.93 page-equivalents, 8 figure labels and 7 table labels. This interval is distinct from the whole file.

Detected heading	PDF page	Estimated span
Supplementary Material	1	≈ 0.02 pp.
7. Proofs	1	≈ 1.6 pp.
8. Datasets Preparation	2	≈ 1.45 pp.
9. Implementation Details	4	≈ 0.74 pp.
10. Complete Quantitative Results	4	≈ 0.94 pp.
11. Visual Results	5	≈ 5.18 pp.

• Table 8 · p. 3
• Figure 9 · p. 4
• Table 9 · p. 4
• Table 10 · p. 5
• Table 11 · p. 5
• Table 12 · p. 5
• Table 13 · p. 5
• Table 14 · p. 6
• Figure 10 · p. 7
• Figure 11 · p. 7
• Figure 12 · p. 7
• Figure 13 · p. 8
• Figure 14 · p. 8
• Figure 15 · p. 9
• Figure 16 · p. 10

Read-only audit 2026-09-26: restored actual supplementary section headings from cached PDF layout, excluding table-of-contents entries and retaining physical PDF page coordinates. This measures reading-order spans, not occupied text area.

Argument and organization

1. Geometric property before implementation

   Introduce diffeomorphic flow and semigroup behavior before the learnable time-conditioned map.

2. Accuracy, topology and cost

   Evaluate registration quality together with topology violations, regularization strength, time sampling and computational cost.

Problem, claim and contribution

The gap is the machinery needed to preserve topology, not simply higher image similarity; the text names integration and auxiliary constraints as the intervention targets.

Abstract and Introduction · Main paper · Additional source 2

Argument and section order

Background gives the group/flow motivation before the proposed partial semigroup loss; detailed proofs are explicitly deferred rather than silently omitted.

Sections 3–4, PDF pp. 3–4 · Main paper · Additional source 2

Figures, captions and visual explanation

The abdominal comparison labels deformable and diffeomorphic variants with suffixes; the lung panel pairs warped anatomy with absolute differences, revealing what visual quality alone could hide.

Figure 4, PDF p. 4; Figure 6, p. 7 · Main paper · Additional source 2

Tables, comparisons and evidence

Tables place registration quality beside negative-Jacobian rates, and the regularization table exposes a quality–topology trade-off instead of presenting only the strongest accuracy setting.

Tables 4–6, PDF p. 7 · Main paper · Additional source 2

Appendix and reproducibility

Proofs and preparation details are followed by complete omitted metrics and anatomical-region boxplots, allowing both mathematical and empirical claims to be traced.

Supplement Sections 7–11, pp. 1–10 · Main paper · Additional source 2

Clarity and writing conventions

The -diff suffix and stated regularization values consistently signal that topology-constrained and relaxed variants are different operating points.

Figure 4 caption and Table 6 · Main paper · Additional source 2

What to reuse—and what not to infer

Transferable lesson: If a method claims a structural guarantee, place that property beside task accuracy in the main tables and explicitly distinguish the constrained and relaxed variants.

Boundary: Numerical zero folding at sampled voxels is not the same as an unrestricted mathematical guarantee. The writing scan records proof placement but does not independently certify the theorem.

Apply this lesson using the argument and evidence worksheet.

Inspection record and sources

Checked

2026-09-26

Reading status

Writing-focused manuscript scan + selected visuals inspected

Main text

Manuscript-wide writing scan of main PDF pp. 1–8: framing, section structure, method exposition, figure/table captions, evaluation organization and conclusions; not an exhaustive technical proof audit or reproduction.

Appendix / supplement

Separate supplement pp. 1–10 scanned: proofs, dataset preparation, implementation, full metric tables, deformation grids and anatomical-region boxplots.

Visually inspected PDF pages

3, 4, 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 CVPR 2026 CVF proceedings PDF; retrieved 2026-09-26 · 11 pages
• Official CVPR 2026 separate supplementary PDF; retrieved 2026-09-26 · 10 pages