ETAP introduces the first event-only tracking-any-point network, trained on a new EventKubric synthetic dataset with a motion-invariance feature-alignment loss, and reports state-of-the-art results on the EDS and EC feature-tracking benchmarks and on TAP-style benchmarks (EventKubric, EVIMO2, E2D2).
Lucas-kanade 20 years on: A unifying frame- work: Part 2
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
background 1
citation-polarity summary
fields
cs.CV 1years
2024 1verdicts
CONDITIONAL 1roles
background 1polarities
background 1representative citing papers
citing papers explorer
-
ETAP: Event-based Tracking of Any Point
ETAP introduces the first event-only tracking-any-point network, trained on a new EventKubric synthetic dataset with a motion-invariance feature-alignment loss, and reports state-of-the-art results on the EDS and EC feature-tracking benchmarks and on TAP-style benchmarks (EventKubric, EVIMO2, E2D2).