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

arXiv:2609.20623 · cs.CV · Submitted 2026-09-17 · Read on arXiv

cs.CV

Submitted: 2026-09-17

Updated: 2026-09-17

Terminology

• Pruning — 52× in this paper · explained in 4 episodes
• Gaussian Splatting — 26× in this paper · explained in 4 episodes
• 3D Gaussian Splatting — 21× in this paper · explained in 2 episodes
• Conference on Computer Vision and Pattern Recognition — 11× in this paper
• Redundancy — 9× in this paper · explained in 2 episodes
• Fidelity — 7× in this paper · explained in 2 episodes
• Importance Mask — 7× in this paper
• Generalization — 5× in this paper · explained in 13 episodes
• Ablation — 4× in this paper · explained in 1 episode
• ACM Transactions on Graphics — 3× in this paper
• Consistency — 3× in this paper · explained in 3 episodes
• Decoupling — 3× in this paper · explained in 2 episodes
• Robustness — 3× in this paper · explained in 5 episodes
• Ablation Studies — 2× in this paper · explained in 1 episode
• Adam — 2× in this paper · explained in 2 episodes
• Alignment — 2× in this paper · explained in 1 episode
• International Conference on Learning Representations — 2× in this paper
• Model-Agnostic — 2× in this paper · explained in 2 episodes
• 3D Gaussian Splatting (3DGS) — 1× in this paper · explained in 4 episodes
• Benchmark — 1× in this paper · explained in 2 episodes
• Core — 1× in this paper · explained in 2 episodes
• Decode — 1× in this paper · explained in 2 episodes
• European Conference on Computer Vision — 1× in this paper
• Fine-Tuning — 1× in this paper · explained in 5 episodes
• Random Mask — 1× in this paper
• Transformer — 1× in this paper · explained in 2 episodes
• Zero-Shot Generalization — 1× in this paper · explained in 5 episodes

Sources

• F4Splat: Feed-Forward Predictive Densification for Feed-Forward 3D Gaussian Splatting
• WorldMirror: Universal 3D World Reconstruction with Any-Prior Prompting
• Diff3R: Feed-forward 3D Gaussian Splatting with Uncertainty-aware Differentiable Optimization
• GlobalSplat: Efficient Feed-Forward 3D Gaussian Splatting via Global Scene Tokens
• ReSplat: Learning Recurrent Gaussian Splatting
• VolSplat: Rethinking Feed-Forward 3D Gaussian Splatting with Voxel-Aligned Prediction

Related papers

• Loss Knows Best: Detecting Annotation Errors in Videos via Loss Trajectories
• AnchorWeave: World-Consistent Video Generation with Retrieved Local Spatial Memories
• Benchmarking the Robustness of Foundation Models for Mammography under Domain Shift
• MambaX-Net: Dual-Input Mamba-Enhanced Cross-Attention Network for Longitudinal MRI Segmentation
• TeleOCR: Navigating Document Parsing Across Digital and Camera-Captured Documents
• A Survey on Efficient Vision-Language-Action Models