CrossFit-GS estimates COLMAP-free poses against a frozen opposite submap

arXivarXivPapers

CrossFit-GS estimates COLMAP-free poses against a frozen opposite submap
arXiv / Zijian Wu, Jinliang Wang and colleagues

Zijian Wu, Jinliang Wang, Mingfeng Jiang, Zidian Lin, Ying Song and Ziqian Lu present CrossFit-GS, a deferred-commitment progressive framework for pose-free 3D Gaussian Splatting from unposed image sequences. The input is partitioned into interleaved subsets that maintain two complementary submaps, and each candidate pose is cross-refined against a frozen opposite submap that has never been optimized using the target frame, providing an independent geometric reference.

Checkerboard validation and spatial coverage safeguards reject unreliable updates, and only verified poses are committed. Once the trajectory is refined, the intermediate submaps are discarded and the final global representation is trained from scratch with the fixed poses. Across multiple benchmarks, the authors report substantially reduced cumulative trajectory drift and improved camera-pose estimation and novel-view synthesis.