- Rating
- 3
- Confidence
- 3
- Informativeness
- 2
- Presentation
- 2
- Soundness
- 3
Read review
Paper summary
This paper proposes P2Voxel, a mesh tokenization framework combining a compact pivot and orientation sign representation, geometry adaptive pyramid sampling, and a block-wise Pyramid VAE. Pivot tokens induce local scalar values for surface extraction, while adaptive resolution allocation reduces the number of sampling primitives. Experiments evaluate direct reconstruction, VAE reconstruction, cross-dataset generalization, and masked latent completion.
Critical strengths
- The framework has a clear motivation and connects representation design, adaptive sampling, and learned compression within a coherent pipeline.
- The reported results demonstrate promising reconstruction and complexity trade-offs across ABO, Objaverse, and Wild. The VAE experiments additionally provide evidence of generalization beyond the training dataset.
- The paper includes useful implementation details, resolution and allocation ablations, and a masked latent completion experiment.
Critical weaknesses
- Moving a projected pivot back inside its voxel may change the recovered surface normal. The paper does not quantify how often this occurs or how much reconstruction error it introduces.
- The experiments combine pivot encoding, adaptive sampling, and VAE compression, making their individual benefits difficult to identify. The implementation and training settings of the VAE baselines also need clarification.
- Token counts and per-token dimensions do not capture the full storage cost. The comparisons lack total latent sizes and the overhead of spatial information and the sampling map.
- The method relies on cross-resolution mesh stitching and hole repair, but their effects on mesh quality and runtime are insufficiently evaluated.
- The “Explicit 3D Representations for Generation” section in Related Works omits recent flow and diffusion-based mesh generation methods, such as MeshFlow, LATO, LATO.2, and Nexus. Discussing these methods would help clarify how P2Voxel differs in its representation design and handling of mesh connectivity.
Questions for authors
- How are pivots outside their voxels handled, and what reconstruction errors does this introduce?
- Can the authors clarify the baseline settings and compare different local encodings using the same adaptive sampling layout?
- Can the authors report total encoded and latent sizes and compare reconstruction quality at matched storage budgets?
- Can the authors report mesh defects before and after stitching and repair, together with the runtime of the current complete pipeline?