DELTAv2: Accelerating Dense 3D Tracking
This accelerates dense 3D tracking for applications like robotics and AR/VR, though it is incremental as it builds on existing transformer-based methods.
The paper tackles the computational inefficiency of dense 3D point tracking in videos by identifying two bottlenecks and proposing a coarse-to-fine strategy with learnable interpolation and an optimization for correlation feature computation, achieving a 5-100x speedup while maintaining state-of-the-art accuracy.
We propose a novel algorithm for accelerating dense long-term 3D point tracking in videos. Through analysis of existing state-of-the-art methods, we identify two major computational bottlenecks. First, transformer-based iterative tracking becomes expensive when handling a large number of trajectories. To address this, we introduce a coarse-to-fine strategy that begins tracking with a small subset of points and progressively expands the set of tracked trajectories. The newly added trajectories are initialized using a learnable interpolation module, which is trained end-to-end alongside the tracking network. Second, we propose an optimization that significantly reduces the cost of correlation feature computation, another key bottleneck in prior methods. Together, these improvements lead to a 5-100x speedup over existing approaches while maintaining state-of-the-art tracking accuracy.