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

2026-09-17

AI Summary

本文提出了一种针对单视图前馈3D高斯重建的后处理剪枝和优化方法，通过重要性评分剪枝和轻量级循环优化模块减少空间冗余并保持图像质量。

Abstract

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 single-view feed-forward 3DGS that couples an importance-score-based pruning mechanism with a trainable, lightweight recurrent refinement module, which iteratively updates the surviving primitives to restore image quality. Our results demonstrate seamless integration with existing baselines while preserving novel-view rendering fidelity and achieving high memory reduction. Furthermore, our method supports flexible inference-time keep ratios for application needs.

Problem

• single-view
• feed-forward
• 3D Gaussian Splatting
• spatial redundancy
• compaction

Innovation

• Post-Hoc Pruning
• Recurrent Refinement
• Single-View 3DGS
• Importance-Score-Based
• Memory Reduction