- Rating
- 3
- Confidence
- 3
- Informativeness
- 2
- Presentation
- 3
- Soundness
- 2
Read review
Paper summary
This paper introduces GeoGSplat, a geometry-grounded feed-forward 3D Gaussian Splatting (3DGS) framework that operates in a non-pixel-aligned paradigm. While existing pixel-aligned methods suffer from a primitive count that scales linearly with input resolution and view count (), recent non-pixel-aligned methods predict a fixed number of Gaussians via learnable tokens but discard explicit ray/depth geometric constraints, leading to poorly placed Gaussian centers and severe rendering artifacts under large viewpoint changes.
Critical strengths
Well-Motivated Hybrid Paradigm Resolving the Efficiency-Geometry Trade-off: The core diagnosis of why non-pixel-aligned 3DGS methods (like TokenGS) fail under large viewpoint changes—namely, photometric overfitting due to underconstrained Gaussian centers—is insightful and empirically well-substantiated (especially in Section 4.3, Figures 5 & 6, and Appendix A.1). By coupling fixed-budget Anchor queries with continuous Triplane feature fields, GeoGSplat maintains a constant primitive count () regardless of whether 2, 4, or 12 views are input, while achieving superior geometric accuracy (Chamfer Distance reduced from to on NRGBD compared to TokenGS) and significantly better extrapolation to distant target views. A common pitfall in large-scale feed-forward 3D vision papers is confounding architectural gains with dataset scaling or supervision differences.
Critical weaknesses
Joint self/cross-attention over Anchor queries and Triplane queries across 12 shared attention blocks.
Two stages of Triplane upsampling up to with 3D-to-2D cross-plane fusion and image-conditioned cross-attention at high spatial resolutions (Eq. 18).
Computing symmetric Chamfer Distance and Farthest Point Sampling (FPS) on points during training (requiring 128 NVIDIA L20 GPUs). Without wall-clock runtime and memory metrics, the claim of "computational efficiency" remains only half-proven (rendering is fast, but encoding/decoding might be a bottleneck).
Questions for authors
Could the authors provide the core specifications deferred to Appendices B, F, H, and I? Specifically: (a) What is the exact base VLM backbone (e.g., Qwen3-VL size)? (b) What are the dataset statistics (number of wafers, lots, operations, classes, and CF-RC test pairs)? (c) What are the details of Table 7 (the 4-phase training schedule) and the computational overhead of multi-attempt rollouts () plus the clue-conditioned forward pass relative to standard GRPO?
Equations (4) and (7) bound the Anchor centers and Triplane queries to via . In Appendix B.5, you mention that during geometric evaluation, "the ground-truth point cloud determines its scale" to normalize the scene into . During inference (before GT geometry is known), how is the scene coordinate frame and scale defined solely from the input camera poses so that unbounded scenes (like Mip-NeRF 360 in Appendix A.3) fit properly inside the Triplane bounds without clipping background geometry?
Why did you choose to compute only on the 4 input views during training rather than held-out target views (which is standard in feed-forward NVS)? Does supervising on novel target views further improve PSNR/LPIPS, or allow the model to rely less on GT depth supervision ()?
In Eq. (8), . Are the learnable offset tokens shared across all Anchors, or distinct per Anchor? Moreover, since already has a 1-to-1 correspondence with the sampled local reference points , why use an all-to-all cross-attention with learnable queries instead of a point-wise MLP or local self-attention directly on ?