- Rating
- 4
- Confidence
- 3
- Informativeness
- 3
- Presentation
- 3
- Soundness
- 3
Read review
Paper summary
This paper presents CoSplat, a feed-forward framework for generalizable surface reconstruction from sparse-view images using 2D Gaussian Splatting. The authors address a key limitation of existing feed-forward Gaussian-based reconstruction methods, where rendering supervision alone may not provide sufficiently accurate geometric constraints, potentially leading to inaccurate surface reconstruction despite plausible novel-view synthesis. To address this issue, the paper introduces two complementary components, Geometry-Calibrated Normal Supervision (GCNS) and Confidence-Guided Tangent-Plane Depth Propagation (TDP). GCNS combines monocular normal priors with geometry-derived normals to provide more reliable normal supervision. TDP improves geometric accuracy by propagating depth hypotheses based on local tangent planes and evaluating their reliability using normal consistency and multi-view geometric confidence. The proposed framework jointly improves surfel orientation and position, enabling more accurate surface reconstruction without requiring expensive per-scene optimization. Extensive experiments on DTU, BlendedMVS, and ETH3D demonstrate competitive reconstruction accuracy and strong generalization capabilities.
Critical strengths
-
The paper addresses an important limitation of existing feed-forward Gaussian-based reconstruction methods, where rendering supervision alone may not sufficiently constrain surface geometry. The motivation is clearly presented, and the proposed approach effectively incorporates complementary geometric constraints to improve reconstruction accuracy.
-
The proposed GCNS and TDP modules are well designed and complement each other effectively. GCNS leverages monocular normal priors while maintaining consistency with predicted geometry, whereas TDP utilizes the resulting normal information to refine depth estimates. Their integration provides a coherent framework for jointly improving surfel orientation and position.
-
The proposed method achieves strong reconstruction accuracy while maintaining efficient feed-forward inference. Experiments across multiple datasets demonstrate its effectiveness and generalization capability. Furthermore, the ablation studies provide convincing evidence of the individual contributions of GCNS and TDP, as well as the benefits of combining these two components.
Critical weaknesses
I did not identify any critical weaknesses in this paper. However, I have a few minor questions and suggestions for clarification, as detailed in the questions for authors.
Questions for authors
-
The experimental results demonstrate the effectiveness of , and the calibration process provides an intuitive way to supervise normals without explicit depth supervision during pretraining. However, and appear to be coupled through the predicted geometry rather than acting as independent supervision terms. Could the authors clarify whether any specific gradient detachment strategy was employed during the calibration process?
-
TDP employs a fixed propagation radius of {} in image space. While this is a reasonable design choice, the spatial extent covered by a fixed pixel-level neighborhood may vary with image resolution, potentially affecting the quality of tangent-plane-based depth propagation. Could the authors clarify whether this formulation is sensitive to input image resolution?
3 comments
Thank you for the clarifications. My questions have been adequately addressed. Regarding Q2, I believe an additional ablation study with different propagation radii would further strengthen the justification for the chosen values.
Thank you for your constructive feedback on the choice of propagation radius. During the design of TDP, we evaluated reconstruction performance with different propagation radii, as shown in the table below.
| Setting | 24 | 37 | 40 | 55 | 63 | 65 | 69 | 83 | 97 | 105 | 106 | 110 | 114 | 118 | 122 | Mean |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| r=1 | 0.76 | 1.87 | 1.30 | 0.85 | 1.17 | 1.26 | 0.68 | 1.01 | 1.16 | 0.74 | 0.82 | 0.58 | 0.47 | 0.87 | 1.00 | 0.97 |
| r=2 | 0.74 | 1.96 | 1.21 | 0.83 | 1.03 | 1.16 | 0.63 | 0.97 | 1.10 | 0.71 | 0.81 | 0.47 | 0.44 | 0.85 | 0.96 | 0.92 |
| r=3 | 0.74 | 1.98 | 1.22 | 0.83 | 1.05 | 1.17 | 0.64 | 0.98 | 1.10 | 0.70 | 0.80 | 0.48 | 0.45 | 0.86 | 0.96 | 0.93 |
The results for r=2 and r=3 are very similar, and the difference may fall within experimental variability. This is partly because reprojection and normal consistency suppress unreliable propagated depth hypotheses. We will release our code after the review process to provide additional implementation details.
Response to Questions
Dear Reviewer,
We sincerely thank you for taking the time to review our paper and for your thoughtful questions of our work. We address your questions below.
Response to Question 1
Thank you for asking about gradient flow in GCNS. We detach the depth-derived normals before low-pass filtering. The resulting geometric reference serves as the target for Lgeo and determines the rotation used to calibrate the monocular normals. We also detach the calibrated target for Lmono. These detachments prevent gradients from either normal loss from flowing back to the depth prediction through its target branch.
Response to Question 2
Thank you for asking about the choice of propagation radii in TDP. In principle, the quality of tangent-plane propagation can be sensitive to input resolution, as the fixed pixel radius covers different physical extents on the surface as the image resolution changes, which can affect the quality of the propagated depth hypotheses. Since resolution also affects reconstruction quality in the absence of TDP, it is difficult to isolate the effect of the propagation radius from changes in overall reconstruction quality. We would also like to explain why we chose these propagation radii:
Our choice of radii is empirical, and this dependence on input resolution is a limitation of the current design.
Thank you again for your time and feedback. We will revised our text later, and our code and model weights will be available after the final decisions.
Reference
[1] Q. Xu and W. Tao. “Multi-Scale Geometric Consistency Guided Multi-View Stereo.” CVPR 2019.