Reliability regulated optimization improves 3d camera tracking accuracy
Reliability-Regulated Trajectory Optimization for Progressive COLMAP-Free 3D Gaussian Splatting
Computer Vision and Pattern Recognition
Summary
Tracking camera positions accurately while building 3D scenes from images is difficult because early mistakes can cause big problems later on. The authors developed a new method that continuously checks and adjusts the camera path by evaluating how trustworthy each step is. This approach helps fix errors both while moving forward and by looking back and adjusting earlier steps without needing external data or complicated setups. Their method leads to clearer 3D reconstructions and better new-view images compared to previous approaches that don't use initial camera poses.
What this means in practice
- •For augmented reality developers: Improve real-time camera trajectory tracking to build more accurate 3D scenes without costly prior steps in AR applications.
- •For robotics navigation teams: Enhance camera-based pose estimation for robots operating in unknown environments by reducing accumulated drift in trajectory calculations.
Authors
Zijian Wu, Jinliang Wang, Zidian Lin, Ying Song, Ziqian Lu, Hanjie Ma, Zhen Ye, Mingfeng Jiang
Abstract
COLMAP-free 3D Gaussian Splatting (3DGS) bypasses computationally expensive structure-from-motion (SfM) pipelines, yet progressive camera pose tracking remains fundamentally vulnerable to error compounding---early pairwise tracking inaccuracies both corrupt subsequent frame initializations and remain permanently frozen in the scene representation. Rather than relying on heavyweight external neural priors or treating progressive tracking through isolated heuristic fixes, we propose a unified reliability-regulated trajectory optimization framework for progressive COLMAP-free 3DGS. At its core, our framework establishes an intrinsic, self-supervised bidirectional cycle-consistency mechanism that systematically regulates progressive camera trajectory estimation across two complementary temporal horizons: (1) Forward Motion Propagation, where the online reliability signal adaptively gates first-order kinematic warm-starts of rigid motion into upcoming pairwise registrations, supplying informed directional search priors while safely intercepting untrusted transitions; and (2) Retrospective Trajectory Correction, where the same reliability signal dynamically weights relative-pose consistency constraints within a sliding window of neighboring camera poses. By governing both prospective state initialization and retrospective trajectory consolidation through a unified reliability regulator, our self-contained framework resolves progressive drift without external priors or offline preprocessing. Extensive evaluations on Tanks and Temples and CO3D-V2 benchmarks show that our method substantially improves camera trajectory accuracy and novel-view rendering quality, outperforming existing unposed baselines. Code is available at https://github.com/Zijian1026/RRTO-CF3DGS.