6 papers
EventPrune: Cascaded Event-Assisted Token Pruning for Efficient First-Person Dynamic Spatial Reasoning
Pengtao Ma, Ziliang Zhou, Ciyu Ruan +7
First-person dynamic spatial reasoning requires models to track continuous motion and precise geometric structure, but the quadratic attention cost of Transformer-based Video-LLMs…
-Fusion: Cross-Modality and Cross-Dimension Flow Estimation in Event Edge Space
Ruishan Guo, Ciyu Ruan, Haoyang Wang +3
Estimating dense 2D optical flow and 3D scene flow is essential for dynamic scene understanding. Recent work combines images, LiDAR, and event data to jointly predict 2D and 3D mot…
Event Camera Meets Mobile Embodied Perception: Abstraction, Algorithm, Acceleration, Application
Haoyang Wang, Ruishan Guo, Pengtao Ma +7
With the increasing complexity of mobile device applications, these devices are evolving toward high agility. This shift imposes new demands on mobile sensing, particularly in achi…
Flight Dynamics to Sensing Modalities: Exploiting Drone Ground Effect for Accurate Edge Detection
Chenyu Zhao, Jingao Xu, Ciyu Ruan +9
Drone-based rapid and accurate environmental edge detection is highly advantageous for tasks such as disaster relief and autonomous navigation. Current methods, using radars or cam…
EDmamba: Rethinking Efficient Event Denoising with Spatiotemporal Decoupled SSMs
Ciyu Ruan, Zihang Gong, Ruishan Guo +2
Event cameras provide micro-second latency and broad dynamic range, yet their raw streams are marred by spatial artifacts (e.g., hot pixels) and temporally inconsistent background…
PRE-Mamba: A 4D State Space Model for Ultra-High-Frequent Event Camera Deraining
Ciyu Ruan, Ruishan Guo, Zihang Gong +3
Event cameras excel in high temporal resolution and dynamic range but suffer from dense noise in rainy conditions. Existing event deraining methods face trade-offs between temporal…