TAP-Vid is a benchmark which contains both real-world videos with accurate human annotations of point tracks, and synthetic videos with perfect ground-truth point tracks. This is designed for a new task called tracking any point.
22 PAPERS • 1 BENCHMARK
PointOdyssey is a large-scale synthetic dataset, and data generation framework, for the training and evaluation of long-term fine-grained tracking algorithms. The dataset currently includes 104 videos, averaging 2,000 frames long, with orders of magnitude more correspondence annotations than prior work.
6 PAPERS • 1 BENCHMARK