Introduces ERGO framework for robust 3D Gaussian splatting from single images. Uses excess risk decomposition to adapt loss weights against noisy views. Adds geometry and texture objectives for fidelity.
Key Points
- 1.Excess risk weighting
- 2.Noise-robust optimization
- 3.SOTA on 3D datasets
Impact Analysis
Advances single-image 3D reconstruction quality. Reduces artifacts in generative supervision.
Technical Details
Decomposes losses into excess risk and Bayes error. Synergistic global-local optimization.