Fusing event-camera data during the 2D-to-3D lifting step improves semantic scene completion accuracy and robustness on a new real-world benchmark and on corrupted SemanticKITTI.
Towards Anytime Optical Flow Estimation with Event Cameras
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
abstract
Event cameras respond to changes in log-brightness at the millisecond level, making them ideal for optical flow estimation. However, existing datasets from event cameras provide only low frame rate ground truth for optical flow, limiting the research potential of event-driven optical flow. To address this challenge, we introduce a low-latency event representation, Unified Voxel Grid, and propose EVA-Flow, an EVent-based Anytime Flow estimation network to produce high-frame-rate event optical flow with only low-frame-rate optical flow ground truth for supervision. Furthermore, we propose the Rectified Flow Warp Loss (RFWL) for the unsupervised assessment of intermediate optical flow. A comprehensive variety of experiments on MVSEC, DESC, and our EVA-FlowSet demonstrates that EVA-Flow achieves competitive performance, super-low-latency (5ms), time-dense motion estimation (200Hz), and strong generalization. Our code will be available at https://github.com/Yaozhuwa/EVA-Flow.
fields
cs.CV 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Event-aided Semantic Scene Completion
Fusing event-camera data during the 2D-to-3D lifting step improves semantic scene completion accuracy and robustness on a new real-world benchmark and on corrupted SemanticKITTI.