InfiniSplat: Implicit Gaussian Decoding for Large-Baseline Monocular View Synthesis
- Published
- Source
- arXiv
- Paper number
- 806
- Field
- Computer Vision
- arXiv ID
- 2608.02437
Key points
- It built an implicit decoder that places Gaussian support points on local surfaces estimated from monocular depth and predicts Gaussian attributes from image features queried at those positions.
- Decoupling support-point placement and attribute prediction from a fixed pixel grid produced a structure that reduces surface cracks and scattered points even under large viewpoint shifts.
- After training only on the synthetic indoor dataset Hypersim, it outperformed existing single-image feed-forward methods on ETH3D, ScanNet++, Tanks and Temples, and DL3DV.
- A single forward pass produces a 3D representation that supports real-time rendering, showing potential for spatial-photo exploration and augmented- and virtual-reality displays.
- Regions unseen in a single image remain unknown, and incorrect depth estimates propagate directly to support-point placement, leaving structural distortions on reflective, transparent, or thin objects and under extreme viewpoint shifts.
Paper links
External research summaries. These are not HDATF publications or measured product results.