Radiance Field-Based Pose Estimation via Decoupled Optimization Under Challenging Initial Conditions

Si-Yu Lu, Yung-Yao Chen, Yi-Tong Wu, Hsin-Chun Lin, Sin-Ye Jhong, Wen-Huang Cheng; Proceedings of the Winter Conference on Applications of Computer Vision (WACV), 2025, pp. 2664-2673

Abstract


Estimating six-degree-of-freedom poses is essential but difficult especially under challenging initial conditions as existing methods relying on photometric loss often fail catastrophically. To address this we propose a novel radiance field-based pose estimation framework that combines Monte Carlo initialization and decoupled optimization. First we design an initialization stage based on Monte Carlo sampling which screens the current optimal initial pose by generating multiple pose hypotheses within the known scene space. Subsequently our decoupled optimization strategy independently refines the rotational and translational components significantly improving the motion stability of the camera during the convergence process. Comprehensive evaluations on synthetic and real-world datasets demonstrate that our method outperforms existing approaches in terms of pose regression accuracy and robustness even under challenging initial pose.

Related Material


[pdf] [supp]
[bibtex]
@InProceedings{Lu_2025_WACV, author = {Lu, Si-Yu and Chen, Yung-Yao and Wu, Yi-Tong and Lin, Hsin-Chun and Jhong, Sin-Ye and Cheng, Wen-Huang}, title = {Radiance Field-Based Pose Estimation via Decoupled Optimization Under Challenging Initial Conditions}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {2664-2673} }