ATSplat: Compact Feed-forward 3D Gaussian Splatting with Adaptive Token Expansion
- Published
- Source
- arXiv
- Paper number
- 696
- Field
- Computer Vision
- arXiv ID
- 2607.20417
Key points
- An adaptive token expansion, or ATE, module automatically finds regions with large rendering error and adds Gaussians there.
- Compared with dense baselines, it reduces the number of Gaussians by more than 5.7x while still reaching state-of-the-art quality.
- It reconstructs 12 images at 512×960 in under 1 second and renders at 1,136 FPS.
- Its 3D anchor-offset design decouples Gaussian placement from the input pixel grid.
- Uncertainty predictions align well with the actual rendering errors, as shown visually.
Paper links
External research summaries. These are not HDATF publications or measured product results.