Writing study: Residual Primitive Fitting of 3D Shapes with SuperFrusta

CVPR overviewCorpus atlasBy contribution typeVisual galleryRules & templateWriting patternsPaper studies

← CVPR 2026 oral writing corpus

Aditya Ganeshan, Matheus Gadelha, Thibault Groueix, Zhiqin Chen, Siddhartha Chaudhuri, Vladimir G. Kim, Wang Yifan, Daniel Ritchie · 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: 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

10 physical pages

Before references / appendix

≈ 8.05 page-equivalents

Main figures / tables

8 / 4

Attached appendix figures / tables

0 / 0

Attached appendix span

Separate file recorded below; not in this PDF total

Before references / appendix: ≈ 80.5%References / intervening material: ≈ 19.5%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	≈ 1.07 pp.	10.7%
2. Residual Primitive Fitting (ResFit): An unsupervised	2	≈ 0.6 pp.	6%
3. Method	3	≈ 2.3 pp.	23%
4. Experiments	5	≈ 2.1 pp.	21%
5. Applications	7	≈ 0.99 pp.	9.9%
6. Conclusion	8	≈ 0.23 pp.	2.3%
References	9	≈ 1.95 pp.	19.5%

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. 6
• Figure 5 · p. 7
• Table 2 · p. 7
• Table 3 · p. 7
• Figure 6 · p. 8
• Table 4 · p. 8
• Figure 7 · p. 8
• Figure 8 · 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 22 physical pages; 13 detected figures and 9 tables. These may include overlapping main-text material.

Detected heading	PDF page	Estimated span
1. Qualitative Examples	1	≈ 0.02 pp.
2. Understanding SuperFrusta	1	≈ 0.02 pp.
3. ResFit Details	1	≈ 0.02 pp.
4. Decomposition & Initialization	1	≈ 0.02 pp.
5. Optimization Details	1	≈ 0.02 pp.
6. Applications	1	≈ 0.02 pp.
7. Additional Experiments	1	≈ 0.02 pp.
8. Failure Cases	1	≈ 19.95 pp.
9. Frequently Asked Questions (FAQs)	21	≈ 0.37 pp.
References	21	≈ 1.31 pp.

• Figure 1 · p. 2
• Figure 2 · p. 3
• Figure 3 · p. 4
• Figure 4 · p. 5
• Figure 5 · p. 6
• Figure 6 · p. 7
• Figure 7 · p. 8
• Figure 8 · p. 10
• Figure 9 · p. 14
• Figure 10 · p. 14
• Table 1 · p. 15
• Table 2 · p. 16
• Table 3 · p. 16
• Table 4 · p. 16
• Table 5 · p. 17
• Table 6 · p. 17
• Table 7 · p. 18
• Table 8 · p. 18
• Figure 11 · p. 19
• Table 9 · p. 19
• Figure 12 · p. 19
• Figure 13 · p. 20

Argument and organization

1. Problem and contribution

   The paper sets up a fidelity–parsimony problem: a reconstruction must fit the shape while remaining a compact program of editable primitives. It then identifies expressivity and fitting strategy as separate obstacles.

2. Argument sequence

   The method introduces residual fitting, the SuperFrustum primitive, shape decomposition and optimization before reporting reconstruction/program quality, ablations and applications. The outline follows the two-part contribution rather than a generic network recipe.

3. Evidence and verification

   Table 1 divides reconstruction quality from program quality, including primitive count, overlap and semantic measures. Some baselines use fewer primitives but fit worse; the table therefore supports a trade-off argument rather than a claim of winning every column.

Problem, claim and contribution

The paper sets up a fidelity–parsimony problem: a reconstruction must fit the shape while remaining a compact program of editable primitives. It then identifies expressivity and fitting strategy as separate obstacles.

Introduction; Figure 1 · Main paper · Additional source 2

Argument and section order

The method introduces residual fitting, the SuperFrustum primitive, shape decomposition and optimization before reporting reconstruction/program quality, ablations and applications. The outline follows the two-part contribution rather than a generic network recipe.

Sections 3–5 · Main paper · Additional source 2

Figures, captions and visual explanation

Figure 2 uses controlled shape variations to explain the eight primitive parameters before equations become central. Pipeline and decomposition figures then explain how residual geometry drives repeated fitting, distinguishing the representation from the algorithm.

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

Tables, comparisons and evidence

Table 1 divides reconstruction quality from program quality, including primitive count, overlap and semantic measures. Some baselines use fewer primitives but fit worse; the table therefore supports a trade-off argument rather than a claim of winning every column.

Table 1, PDF p.6 · Main paper · Additional source 2

Appendix and reproducibility

A roadmap opens the unusually long supplement, which develops signed-distance constructions, supplies fitting algorithms, documents optimization/applications and adds ablations, failures and a FAQ. This is a strong example of navigating a derivation-heavy appendix by purpose.

Supplementary PDF pp.1–22; Algorithms 1–2 around pp.10–11; failure discussion around p.20 · Main paper · Additional source 2

Clarity and writing conventions

The main text names a fixed evaluation budget and separates test-time optimization variants in the comparison. This keeps an algorithmic improvement from being confused with an unreported larger search budget.

Implementation and comparisons, Section 4.1, PDF p.6 · Main paper · Additional source 2

What to reuse—and what not to infer

Transferable lesson: For structured reconstruction, define both output fidelity and representation simplicity, illustrate primitive controls, then evaluate the two objectives in separate column groups.

Boundary: Here residual means iterative unexplained geometry, not residual knowledge distillation. Compactness, semantic interpretability and geometric accuracy remain distinct outcomes.

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

Writing-oriented scan throughout main PDF pp.1–8 and references pp.9–10: abstract/framing, section sequence, figure/table captions, evaluation organization and conclusions; not an exhaustive technical verification.

Appendix / supplement

Writing-oriented supplement scan: all 22 supplementary PDF pages scanned for derivation, algorithm, experiment and limitation organization, not exhaustive formula verification. Video/code assets were not executed or assessed.

Visually inspected PDF pages

2, 6

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 CVPR 2026 accepted-paper PDF · 10 pages
• Official CVF supplementary PDF · 22 pages