SOURCE-LINKED INTELLIGENCE

PhGS: Post-Hoc Pruning and Refinement of Single-View Feed-Forward 3D Gaussian Reconstructions

arXiv · AI, language, vision and robotics · article · Sep 17, 2026 · UTC

Recent single-view feed-forward 3D Gaussian Splatting (3DGS) generation predicts a fixed number of Gaussians per camera ray, introducing severe spatial redundancy. Most existing compaction strategies target multi-view setups to exploit cross-view consistency and are incompatible with single-image models. Instead of retraining the base feed-forward network to directly output compact representations, our insight is to keep the base models frozen and apply post-hoc pruning and recurrent refinement to the generated Gaussians. Consequently, we propose a backbone-agnostic compaction pipeline for sin

Read original source ↗ Open in workspace

recordType

paper

region

Global