StereoGaussians: Feed-Forward 3D Gaussian Splatting from Stereo Images

arXiv:2609.38592v1 Announce Type: new Abstract: Feed-forward 3D Gaussian Splatting (3DGS) enables reconstruction without per- scene optimisation, but practical stereo-camera applications require nearby-view extrapolation beyond the input views. Stereo depth anchors visible surfaces, yet rendering newly exposed regions also requires learned appearance and additional scene capacity. We introduce StereoGaussians, which predicts a metric 3DGS representation from a single calibrated stereo pair. It reuses intermediate repre- sentations from frozen pretrained stereo networks to predict Gaussian attributes, while calibrated disparity anchors the geometry. A second Gaussian layer and an expanded image canvas provide capacity for disoccluded and outside-field-of- view content. For training, we construct SceneSplat-Stereo from quality-filtered 3DGS teachers, pairing stereo inputs with nearby target views across 803 training scenes. Experiments on unseen real and photorealistic stereo benchmarks demon- strate improvements over strong view-synthesis baselines, while ablation studies support our main design choices.

Related

• GrapeSplat: Geometry-Grounded Reconstruction via Amalgamated Pose-Free Encoding for Feed-Forward 3D Gaussian Splatting
• AVSplat: Dense-View Feed-Forward 3D Gaussian Splatting with Assist-View Preconditioning
• CoMVS-GS: Collaborative Multi-View Stereo and 3D Gaussian Splatting for Surface Reconstruction
• FlexSplat: Flexible Feed-Forward 3D Gaussian Splatting without Point Cloud Correspondence

Source: arXiv cs.CV | 2026-10-01