D$^2$USt3R: Enhancing 3D Reconstruction for Dynamic Scenes
This addresses the challenge of 3D reconstruction for dynamic scenes in computer vision, but it is incremental as it builds on prior static methods.
The paper tackles the problem of 3D reconstruction in dynamic scenes, where object motions degrade existing methods like DUSt3R, and proposes D^2USt3R to regress Static-Dynamic Aligned Pointmaps, achieving superior performance across datasets with complex motions.
In this work, we address the task of 3D reconstruction in dynamic scenes, where object motions frequently degrade the quality of previous 3D pointmap regression methods, such as DUSt3R, that are originally designed for static 3D scene reconstruction. Although these methods provide an elegant and powerful solution in static settings, they struggle in the presence of dynamic motions that disrupt alignment based solely on camera poses. To overcome this, we propose $D^2USt3R$ that directly regresses Static-Dynamic Aligned Pointmaps (SDAP) that simultaneiously capture both static and dynamic 3D scene geometry. By explicitly incorporating both spatial and temporal aspects, our approach successfully encapsulates 3D dense correspondence to the proposed pointmaps, enhancing downstream tasks. Extensive experimental evaluations demonstrate that our proposed approach consistently achieves superior 3D reconstruction performance across various datasets featuring complex motions.