- Rating
- 3(+1)
- Confidence
- 2
- Informativeness
- 2
- Presentation
- 3
- Soundness
- 3
Read review
Paper summary
This paper presents AnchorGen, a framework for physics-driven 3D shape optimization that incorporates 2D sketches to preserve and control design intent. The method first encodes 3D shapes and their corresponding sketches into separate latent representations, which are then concatenated to train an unconditional joint flow matching model. During inference, the framework optimizes an intermediate state of the learned flow by combining a differentiable aerodynamic drag objective with a sketch anchoring loss based on token-wise cosine similarity. This allows the shape and sketch representations to evolve jointly while encouraging the generated geometry to remain consistent with a target sketch. The framework supports three applications: optimizing an existing shape while preserving its design, modifying specific geometric features through edited sketches, and generating 3D shapes from sketches without an initial model. The authors evaluate AnchorGen on ShapeNet and DrivAerNet++, comparing it with prior-based optimization methods and sketch-conditioned generative approaches. The experiments examine aerodynamic drag reduction, geometric similarity, dimensional control, and shape preservation, along with additional analyses of sketch guidance strength, model capacity, and generation from sparse sketches.
Critical strengths
This work introduces 2D sketches into physics-driven 3D shape optimization, allowing users to express their design intentions through intuitive and easily editable sketches. By incorporating sketch-based constraints into the optimization process, the method improves the controllability and flexibility of 3D shape design.
Critical weaknesses
-
Limited Novelty. Previous studies have already incorporated physics-based optimization into 3D generation. This work mainly extends existing approaches by jointly modeling 2D sketches and 3D shapes while optimizing both sketch consistency and physical performance. Therefore, the methodological novelty appears relatively limited.
-
Limited Generalization. Although the paper presents AnchorGen as a general framework for generative 3D design, all experiments focus on automotive shapes and aerodynamic drag optimization. The authors should consider evaluating additional shape categories and physical objectives or narrowing the scope of their claims to better align with the experimental evidence.
Questions for authors
-
What is the specific advantage of jointly modeling 2D sketches and 3D shapes compared to simply adding a sketch consistency loss to an existing physics-guided shape optimization framework? Could the authors provide an ablation to better isolate the contribution of joint modeling?
-
The paper presents AnchorGen as a general framework for generative 3D design, but the experiments focus exclusively on automotive shapes and drag optimization. Is there any evidence that the method generalizes to other shape categories or physical objectives? If not, could the authors clarify the scope and limitations of the proposed framework?
4 comments
Author Responses (2)
W2 / Q2. Generalization to Other Shape Categories and Physical Objectives.
The paper presents AnchorGen as a general framework for generative 3D design, but the experiments focus exclusively on automotive shapes and drag optimization. Is there any evidence that the method generalizes to other shape categories or physical objectives?...
A: The reviewer is right and we addressed this concern by adding a chair volume-reduction experiment (Sec. 4.4). In the spirit of those in FCSO, we reduce the volume of each chair by 15%, which would make it lighter, save material, and lower its production cost in real industrial settings.
-
Truly different. Unlike drag, which is predicted by a learned surrogate, volume is computed directly from the shape. Yet minimizing it can easily destroy realism: thin legs break, holes appear in the backrest, or the chair turns into a generic boxy one. This makes it a direct test of whether the optimization preserves the original design, complementing the experiments on cars.
-
Setup. A single model is trained on synthetic sketches and anchored at test time to real hand-drawn sketches of 30 held-out chairs from three views. AnchorGen again consistently stays closer to the original chair than all baselines on most metrics as reported in the table below.
Fig. 5 and Fig. 15 of the revised paper provide qualitative results showing that it preserves the initial design, whereas the baselines break thin legs, fill the backrest slots, or make the chair boxy. The table below reports the similarity of each optimized chair to its own original shape at a 15% volume reduction, separately for each sketch view (all metrics are scaled by ×100). More details are given in Appendix H.
| Method | F@1% ↑ | [email protected]% ↑ | CD-L1 ↓ | Vol-Ratio ↑ | Normal-C ↑ | HD95 ↓ | Avg. Dim-Err ↓ |
|---|---|---|---|---|---|---|---|
| GD (2025) | 94.82 | 70.25 | 0.90 | 84.13 | 96.95 | 1.05 | 1.83 |
| FMG (2022) | 57.39 | 34.71 | 3.20 | 85.46 | 82.09 | 5.36 | 4.03 |
| D-Flow (2024) | 59.39 | 37.04 | 3.78 | 80.95 | 82.06 | 7.59 | 5.71 |
| ICTM (2024) | 54.05 | 32.25 | 3.10 | 76.52 | 80.17 | 5.81 | 6.61 |
| SGO (2026) | 95.62 | 73.58 | 0.85 | 83.94 | 97.58 | 0.92 | 1.62 |
| FCSO (2026) | 92.66 | 71.45 | 0.97 | 83.84 | 96.51 | 1.32 | 1.98 |
| AnchorGen (0°) | 97.92 | 83.22 | 0.77 | 83.85 | 98.13 | 0.90 | 1.05 |
| AnchorGen (45°) | 97.38 | 82.86 | 0.83 | 83.98 | 97.85 | 1.02 | 1.11 |
| AnchorGen (90°) | 98.03 | 82.44 | 0.79 | 83.95 | 98.03 | 0.95 | 1.11 |
Thank you for the responses and additional experiments. The new comparisons help explain why directly using sketch projections is less effective and clarify the motivation behind the joint modeling approach. The chair experiment also helps address my concern about the method's applicability beyond automotive design. While further tests on other categories would still be useful, the authors have addressed my main concerns, and I am satisfied with the revisions.
Thank You for Your Feedback
Dear Reviewer 2u5r,
Thank you for your positive feedback and for acknowledging our revisions. We truly appreciate your time and constructive comments.
Best regards,
AnchorGen Authors
Author Responses (1)
W1 / Q1. Joint Modeling vs. Sketch Consistency Loss.
A: Our goal is to preserve the design style specified by a sketch during physics-driven optimization. Existing methods either only keep the shape on the manifold of valid shapes and ignore its style, as FCSO does, or require the user to explicitly specify which existing features to preserve, as GANO [1] does through null-space projection. Neither keeps the overall style that a sketch expresses.
As the reviewer suggests, the simplest way to achieve our stated goal would be to incorporate a sketch consistency loss into an existing physics-guided shape optimization framework, which is similar in spirit to Sketch2Mesh [2]. Unfortunately, this is not as easy or effective as it sounds:
Our design avoids the first two problems and mitigates the third: the anchor is a cosine distance in the sketch latent space, so no projector or rendering is needed, and since the correspondence between shape and sketch is learned from data, comparing latent tokens rather than pixels is less sensitive to the drawing style.
[1] Guoze, Sun, et al. "Geometry-Aware Neural Optimizer for Shape Optimization and Inversion." Forty-third International Conference on Machine Learning.
[2] Guillard, Benoit, et al. "Sketch2mesh: Reconstructing and editing 3d shapes from sketches." 2021 IEEE/CVF International Conference on Computer Vision (ICCV). IEEE, 2021.