StructSplat: Generalizable 3D Gaussian Splatting from Uncalibrated Images
Field: Computer Vision Authors: Jia-Chen Zhao, Beiqi Chen, Xinyang Chen Published: 2026-06-26 arXiv: 2606.28321
Abstract
We present StructSplat, a feed-forward and generalizable 3D Gaussian reconstruction framework that operates directly on uncalibrated images without requiring camera parameters. Existing methods either rely on per-scene optimization or assume known camera poses, and often entangle geometry and appearance within a unified backbone, limiting reconstruction fidelity and generalization.
Our key idea is to adopt a structured representation that organizes geometry, semantic, and texture cues with explicit roles in the reconstruction process. Specifically:
- Pixel-aligned feature injection: enables accurate texture modeling from 2D observations.
- Semantic-aware priors: improve global consistency across the scene.
- Camera alignment strategy: prevents information leakage and improves generalization.
- DL3DV: 28.045 PSNR, exceeding AnySplat (22.377) by +5.67 dB.
- Cross-dataset evaluation: +1.94 dB over AnySplat on ACID and +1.72 dB on RealEstate10K.
Results
Experiments show that StructSplat significantly outperforms prior methods on challenging benchmarks:
*Auto-collected on 2026-06-30.*