Search papers, labs, and topics across Lattice.
Track4World is introduced as a feedforward model for efficient, dense 3D tracking of every pixel in a monocular video within a world-centric coordinate system. The model employs a VGGT-style ViT to encode a global 3D scene representation and introduces a novel 3D correlation scheme for simultaneous estimation of pixel-wise 2D and 3D dense flow between frames. Experiments on multiple benchmarks demonstrate that Track4World outperforms existing methods in 2D/3D flow estimation and 3D tracking.
Unlock real-time, holistic 3D tracking of every pixel in a video with Track4World, a feedforward model that leapfrogs past slow, optimization-based methods.
Estimating the 3D trajectory of every pixel from a monocular video is crucial and promising for a comprehensive understanding of the 3D dynamics of videos. Recent monocular 3D tracking works demonstrate impressive performance, but are limited to either tracking sparse points on the first frame or a slow optimization-based framework for dense tracking. In this paper, we propose a feedforward model, called Track4World, enabling an efficient holistic 3D tracking of every pixel in the world-centric coordinate system. Built on the global 3D scene representation encoded by a VGGT-style ViT, Track4World applies a novel 3D correlation scheme to simultaneously estimate the pixel-wise 2D and 3D dense flow between arbitrary frame pairs. The estimated scene flow, along with the reconstructed 3D geometry, enables subsequent efficient 3D tracking of every pixel of this video. Extensive experiments on multiple benchmarks demonstrate that our approach consistently outperforms existing methods in 2D/3D flow estimation and 3D tracking, highlighting its robustness and scalability for real-world 4D reconstruction tasks.
