ConfidentSplat: Confidence-Weighted Depth Fusion for Accurate 3D Gaussian Splatting SLAM
This advances dense visual SLAM for applications like robotics and AR/VR by addressing a key bottleneck in RGB-only methods, though it builds incrementally on existing 3DGS and SLAM frameworks.
The paper tackles geometric inaccuracies in RGB-only 3D Gaussian Splatting SLAM by introducing ConfidentSplat, which uses confidence-weighted depth fusion to integrate multiview geometry with learned priors, resulting in significant improvements in reconstruction accuracy and novel view synthesis fidelity on benchmarks like TUM-RGBD and ScanNet.
We introduce ConfidentSplat, a novel 3D Gaussian Splatting (3DGS)-based SLAM system for robust, highfidelity RGB-only reconstruction. Addressing geometric inaccuracies in existing RGB-only 3DGS SLAM methods that stem from unreliable depth estimation, ConfidentSplat incorporates a core innovation: a confidence-weighted fusion mechanism. This mechanism adaptively integrates depth cues from multiview geometry with learned monocular priors (Omnidata ViT), dynamically weighting their contributions based on explicit reliability estimates-derived predominantly from multi-view geometric consistency-to generate high-fidelity proxy depth for map supervision. The resulting proxy depth guides the optimization of a deformable 3DGS map, which efficiently adapts online to maintain global consistency following pose updates from a DROID-SLAM-inspired frontend and backend optimizations (loop closure, global bundle adjustment). Extensive validation on standard benchmarks (TUM-RGBD, ScanNet) and diverse custom mobile datasets demonstrates significant improvements in reconstruction accuracy (L1 depth error) and novel view synthesis fidelity (PSNR, SSIM, LPIPS) over baselines, particularly in challenging conditions. ConfidentSplat underscores the efficacy of principled, confidence-aware sensor fusion for advancing state-of-the-art dense visual SLAM.