Tracktention: Leveraging Point Tracking to Attend Videos Faster and Better
This addresses the challenge of maintaining coherent outputs in video prediction for applications like video processing, though it is incremental as it builds on existing models like Vision Transformers.
The paper tackles the problem of temporal consistency in video prediction by proposing the Tracktention Layer, which integrates motion information using point tracks to enhance alignment and handle complex object motions, resulting in significantly improved temporal consistency in tasks like video depth prediction and colorization compared to baselines.
Temporal consistency is critical in video prediction to ensure that outputs are coherent and free of artifacts. Traditional methods, such as temporal attention and 3D convolution, may struggle with significant object motion and may not capture long-range temporal dependencies in dynamic scenes. To address this gap, we propose the Tracktention Layer, a novel architectural component that explicitly integrates motion information using point tracks, i.e., sequences of corresponding points across frames. By incorporating these motion cues, the Tracktention Layer enhances temporal alignment and effectively handles complex object motions, maintaining consistent feature representations over time. Our approach is computationally efficient and can be seamlessly integrated into existing models, such as Vision Transformers, with minimal modification. It can be used to upgrade image-only models to state-of-the-art video ones, sometimes outperforming models natively designed for video prediction. We demonstrate this on video depth prediction and video colorization, where models augmented with the Tracktention Layer exhibit significantly improved temporal consistency compared to baselines.