Research map / 3D vision / Gaussian splatting
Can3Tok: Canonical 3D Tokenization and Latent Modeling of Scene-Level 3D Gaussians
Quankai Gao, Iliyan Georgiev, Tuanfeng Y. Wang, Krishna Kumar Singh, Ulrich Neumann, Jae Shin Yoon
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| add learnable latent query (ablation) | Can3Tok · DL3DV-10K test | L2 error: 10^25 -> 30.1 | Improved |
| add 3DGS normalization (ablation) | Can3Tok · DL3DV-10K test | L2 error: 1889.7 -> 30.1 | Improved |
| add voxel coordinate appending (ablation) | Can3Tok · DL3DV-10K test | L2 error: 50.5 -> 30.1 | Improved |
| add semantic-aware data filtering (ablation) | Can3Tok · DL3DV-10K test | L2 error: 73.3 -> 30.1 | Improved |
| add SO(3) rotation augmentation (ablation) | Can3Tok · DL3DV-10K test | L2 error: 53.3 -> 30.1 | Improved |
| add voxel coordinate appending (ablation) | Can3Tok · DL3DV-10K test | failure rate (%): 4.3 -> 2.5 | Improved |
| add semantic-aware data filtering (ablation) | Can3Tok · DL3DV-10K test | failure rate (%): 6.1 -> 2.5 | Improved |
| add SO(3) rotation augmentation (ablation) | Can3Tok · DL3DV-10K test | failure rate (%): 4.6 -> 2.5 | Improved |
| replace baseline VAE architectures with Can3Tok | PointTransformer · DL3DV-10K test | L2 error: 230.7 -> 30.1 | Improved |
Closest papers by meaning
- LT3SD: Latent Trees for 3D Scene Diffusion (CVPR 2025 · similarity 0.89)
- A 3D Scene is Worth 1K Tokens: 3D-Grounded Representation for Scene Generation at Scale (NeurIPS 2026 · similarity 0.89)
- PartCrafter: Structured 3D Mesh Generation via Compositional Latent Diffusion Transformers (NeurIPS 2025 · similarity 0.89)
- SAR3D: Autoregressive 3D Object Generation and Understanding via Multi-scale 3D VQVAE (CVPR 2025 · similarity 0.88)
- LaGeM: A Large Geometry Model for 3D Representation Learning and Diffusion (ICLR 2025 · similarity 0.88)
- Structured 3D Latents for Scalable and Versatile 3D Generation (CVPR 2025 · similarity 0.87)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.
