TraqPoint uses a track-aware reward and policy gradients in RL to train keypoint detectors for better trackability across sequences, outperforming prior methods on matching and reconstruction benchmarks.
RIPE: Reinforcement learning on unlabeled image pairs for robust keypoint extraction
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
From Pairs to Sequences: Track-Aware Policy Gradients for Keypoint Detection
TraqPoint uses a track-aware reward and policy gradients in RL to train keypoint detectors for better trackability across sequences, outperforming prior methods on matching and reconstruction benchmarks.