arXiv AI By Kangmin Seo, Jae-Pil Heo

Per-View Gaussian Predictions Enable Training-Free Distractor Filtering in Feed-Forward 3DGS

Read the original on arXiv AI →

The paper presents a training‑free filtering method for feed‑forward 3D Gaussian Splatting that removes transient distractors from 3D reconstructions. By excluding each input’s per‑view Gaussians and re‑rendering the scene, the method identifies inconsistent content through feature similarity and reconstruction error reduction. The approach improves novel‑view quality across multiple models and benchmarks while preserving clean scenes.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv AI.

arXiv Computer Vision
Aug 27

3DGS-HPC: Distractor-free 3D Gaussian Splatting with Hybrid Patch-wise Classification

3DGS-HPC is a framework that improves 3D Gaussian Splatting for novel view synthesis by mitigating transient distractors such as moving objects and varying shadows. It combines a patch‑wise classification strategy that uses local spatial consistency for robust region‑level decisions with a hybrid classification metric that adaptively integrates photometric and perceptual cues. Experiments show that this approach outperforms existing methods in reducing distractor effects and enhancing 3DGS quality.

By Jiahao Chen, Yipeng Qin, Ganlong Zhao, Xin Li, Wenping Wang, Guanbin Li
Hugging Face Trending Papers
Aug 11

CasDeblurGS: Cascaded 2D-to-3D Multi-View Consistency for 3D Gaussian Splatting from Two Blurry Images

Free-viewpoint 3D scene media is increasingly important for immersive applications, yet practical capture often suffers from severe view sparsity and motion blur. Although neural rendering has advanced sparse-view synthesis, existing blur-aware methods typically require substantial multi-view redundancy, accurate camera poses, or costly per-scene optimization.