Model Releases
AnchorSplat: Feed-Forward 3D Gaussian Splatting with 3D Geometric Priors
arXiv:2604.07053v2 Announce Type: replace Abstract: Recent feed-forward Gaussian reconstruction models adopt a pixel-aligned formulation that maps each 2D pixel to a 3D Gaussian, entangling Gaussian r
arXiv:2604.07053v2 Announce Type: replace Abstract: Recent feed-forward Gaussian reconstruction models adopt a pixel-aligned formulation that maps each 2D pixel to a 3D Gaussian, entangling Gaussian representations tightly with the input images. In this paper, we propose AnchorSplat, a novel feed-forward 3DGS framework for scene-level reconstruction that represents the scene directly in 3D space. AnchorSplat introduces an anchor-aligned Gaussian representation guided by 3D geometric priors (e.g., sparse point clouds, voxels, or RGB-D point clouds), enabling a more geometry-aware renderable 3D Gaussians that is independent of image resolution and number of views. This design substantially reduces the number of required Gaussians, improving computational efficiency while enhancing reconstruction fidelity. Beyond the anchor-aligned design, we utilize a Gaussian Refiner to adjust the intermediate Gaussiansy via merely a few forward passes. Experiments on the ScanNet++ v2 NVS benchmark demonstrate the SOTA performance, outperforming previous methods with more view-consistent and substantially fewer Gaussian primitives.
Related
- CryoSplat: Gaussian Splatting for Cryo-EM Homogeneous Reconstruction
- PhyEdit: Towards Real-World Object Manipulation via Physically-Grounded Image Editing
- You Point, I Learn: Online Adaptation of Interactive Segmentation Models for Handling Distribution Shifts in Medical Imaging
- PSR: Scaling Multi-Subject Personalized Image Generation with Pairwise Subject-Consistency Rewards
- CryoSplat: Gaussian Splatting for Cryo-EM Homogeneous Reconstruction
- PhyEdit: Towards Real-World Object Manipulation via Physically-Grounded Image Editing
Source: arXiv cs.CV | 2026-04-10