Complet4R: Geometric Complete 4D Reconstruction
This work addresses the challenge of reconstructing complete 4D geometry from video, benefiting applications in computer vision and graphics that require dynamic scene understanding.
Complet4R introduces an end-to-end framework for 4D reconstruction that recovers temporally coherent and geometrically complete dynamic scenes, achieving state-of-the-art performance on a new benchmark and the 3D Point Tracking task.
We introduce Complet4R, a novel end-to-end framework for Geometric Complete 4D Reconstruction, which aims to recover temporally coherent and geometrically complete reconstruction for dynamic scenes. Our method formalizes the task of Geometric Complete 4D Reconstruction as a unified framework of reconstruction and completion, by directly accumulating full contexts onto each frame. Unlike previous approaches that rely on pairwise reconstruction or local motion estimation, Complet4R utilizes a decoder-only transformer to operate all context globally directly from sequential video input, reconstructing a complete geometry for every single timestamp, including occluded regions visible in other frames. Our method demonstrates the state-of-the-art performance on our proposed benchmark for Geometric Complete 4D Reconstruction and the 3D Point Tracking task. Code will be released to support future research.