ClearGS: Reliability-Aware Gaussian Splatting from Handheld Videos

arXiv:2609.31509 · cs.CV, cs.AI · Submitted 2026-09-25 · Read on arXiv

cs.CV, cs.AI

Submitted: 2026-09-25

Updated: 2026-09-25

Terminology

• Gaussian Splatting — 24× in this paper · explained in 4 episodes
• 3D Gaussian Splatting — 10× in this paper · explained in 2 episodes
• Distillation — 8× in this paper · explained in 2 episodes
• Ablation — 4× in this paper · explained in 1 episode
• Regularization — 3× in this paper · explained in 3 episodes
• Reliability-aware View Allocation — 3× in this paper
• 3D Gaussian Splatting (3DGS) — 2× in this paper · explained in 4 episodes
• Gaussian Splatting on the Move — 2× in this paper
• Information Gain — 2× in this paper · explained in 2 episodes
• Redundancy — 2× in this paper · explained in 2 episodes
• Transformer — 2× in this paper · explained in 2 episodes
• Ablation study — 1× in this paper · explained in 1 episode
• Adaptation — 1× in this paper · explained in 1 episode
• Aggregation — 1× in this paper · explained in 1 episode
• Diffusion Model — 1× in this paper · explained in 8 episodes
• Diffusion Models — 1× in this paper · explained in 6 episodes
• RenderGuided In-Video Restoration — 1× in this paper

Sources

• Qwen3-VL Technical Report
• GeoQuery: Geometry-Query Diffusion for Sparse-View Reconstruction
• SyncFix: Fixing 3D Reconstructions via Multi-View Synchronization
• G4Splat: Geometry-Guided Gaussian Splatting with Generative Prior
• ActiveInitSplat: How Active Image Selection Helps Gaussian Splatting
• Sparse-to-Complete: From Sparse Image Captures to Complete 3D Scenes
• D$^2$GS: Depth-and-Density Guided Gaussian Splatting for Stable and Accurate Sparse-View Reconstruction
• GSFixer: Improving 3D Gaussian Splatting with Reference-Guided Video Diffusion Priors

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