ClearGS: Reliability-Aware Gaussian Splatting from Handheld Videos

2026-09-25

AI Summary

This study addresses the challenges of 3D Gaussian Splatting reconstruction from handheld videos, where uneven view coverage and mixed image quality degrade performance. To overcome these issues, this work proposes a reliability-aware view allocation framework. Departing from conventional binary frame selection, it introduces hierarchical weight-based supervision. Furthermore, by integrating rendering-guided reference-free image restoration with a full-trajectory integration mechanism, the method recovers fine details while preserving complete trajectory coverage in the absence of clear references. Experimental results demonstrate that the proposed approach achieves state-of-the-art performance on both the GS2E and GSOTM datasets. It significantly improves CLIP-IQA and MUSIQ scores while reducing LPIPS error, thereby enabling high-quality 3D reconstruction.

Abstract

We present ClearGS for 3D Gaussian Splatting (3DGS) from handheld videos with uneven viewpoint coverage and mixed frame quality. Rather than selecting frames with binary decisions, ClearGS uses Reliability-aware View Allocation (RVA) to assign graded raw-supervision weights based on appearance reliability, degradation risk, and geometric utility, while weakly reactivating useful suppressed frames to maintain trajectory coverage. Since weighting cannot restore details lost to blur or distortion, ClearGS further introduces Render-Guided In-Video Restoration (RIVR). The current 3DGS render provides a pose-aligned structural candidate, a frozen no-reference restoration expert restores the corresponding raw video observation without any clean reference image, and no-reference perceptual scores select among the render, restored observation, and high-frequency fused candidate. ClearGS then applies Full-Trajectory Repair Consolidation to revisit accepted repairs and preserve details introduced early. On GS2E and GSOTM, ClearGS achieves state-of-the-art overall performance, with consistent CLIP-IQA and MUSIQ gains and LPIPS reductions in most degradation settings, without paired sharp supervision or matched clean references.

Problem

• 3D Gaussian Splatting
• handheld videos
• uneven viewpoint coverage
• mixed frame quality
• image degradation

Innovation

• 3D Gaussian Splatting
• Reliability-aware View Allocation
• Render-Guided In-Video Restoration
• No-reference Restoration
• Full-Trajectory Repair Consolidation