MrNeRF (@janusch_patas)
2024-10-07 | โค๏ธ 630 | ๐ 86
MonST3R: A Simple Approach for Estimating Geometry in the Presence of Motion
TL;DR: DUSt3R keeps impressing.
Contributions (cited): โข We introduce Motion DUSt3R (MonST3R), a geometry-first approach to dynamic scenes that directly estimates geometry in the form of pointmaps, even for moving scene elements.
To this end, we identify several suitable datasets and show that, surprisingly, a small-scale fine-tuning achieves promising results for direct geometry estimation of dynamic scenes.
โข MonST3R obtains promising results on several downstream tasks (video depth and camera pose estimation). In particular, MonST3R offers key advantages over prior work: enhanced robustness, particularly in challenging scenarios; increased speed compared to optimization-based methods; and competitive results with specialized techniques in video depth estimation, camera pose estimation and dense reconstruction.
๋ฏธ๋์ด
