EPO: Boosting 3D Foundation Models with Edge-based Pose Optimization
For practitioners using 3D Foundation Models, EPO provides a fast, memory-efficient post-processing method to improve geometric accuracy without sacrificing speed.
EPO is a trackless geometric optimization framework that boosts the accuracy of 3D Foundation Model reconstructions by using edge map alignment, matching or outperforming Bundle Adjustment while requiring less runtime and memory, and enabling operation on consumer-grade hardware.
We introduce \textbf{Edge-based Pose Optimization (EPO)}, a trackless geometric optimization framework specifically designed to boost the Structure-from-Motion reconstructions generated by 3D Foundation Models. These models achieve rapid inference by bypassing the time-consuming feature extraction and matching stages of traditional pipelines, where explicit correspondences between each 3D point and multiple images, referred to as tracks, are established. However, their geometric accuracy currently falls short of traditional pipelines. While this can be addressed in a post-processing step via Bundle Adjustment-like refinement, doing so requires extracting feature tracks, thus defeating the original speed advantage. Instead, our fully differentiable framework uses edge map alignment as a proxy for geometric optimization, avoiding feature extraction and track construction entirely. Through extensive evaluation across multiple datasets and tasks, we demonstrate that EPO matches or outperforms Bundle Adjustment-like methods while requiring significantly lower runtime and memory. Notably, its reduced memory footprint makes EPO suitable for consumer-grade hardware, where competing refinement methods cannot run.