TL;DR
Event6D leverages event cameras for real-time 6D object pose tracking in fast scenes, using a novel framework that generalizes to new objects without specific training.
Contribution
Introduces EventTrack6D, a framework for event-based 6D pose tracking that operates at over 120 FPS and generalizes to unseen objects without fine-tuning.
Findings
Operates at over 120 FPS with temporal consistency.
Generalizes effectively to real-world scenarios without fine-tuning.
Validated on a new synthetic dataset and real-world benchmarks.
Abstract
Event cameras provide microsecond latency, making them suitable for 6D object pose tracking in fast, dynamic scenes where conventional RGB and depth pipelines suffer from motion blur and large pixel displacements. We introduce EventTrack6D, an event-depth tracking framework that generalizes to novel objects without object-specific training by reconstructing both intensity and depth at arbitrary timestamps between depth frames. Conditioned on the most recent depth measurement, our dual reconstruction recovers dense photometric and geometric cues from sparse event streams. Our EventTrack6D operates at over 120 FPS and maintains temporal consistency under rapid motion. To support training and evaluation, we introduce a comprehensive benchmark suite: a large-scale synthetic dataset for training and two complementary evaluation sets, including real and simulated event datasets. Trained…
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Code & Models
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
