activity
20242026
collaborators

5 papers

cs.CV2026

RAFT-MSF++: Temporal Geometry-Motion Feature Fusion for Self-Supervised Monocular Scene Flow

Xunpei Sun, Zuoxun Hou, Yi Chang +2

Monocular scene flow estimation aims to recover dense 3D motion from image sequences, yet most existing methods are limited to two-frame inputs, restricting temporal modeling and r…

cs.CV2026

UFlow: Uncertainty-Aware Unsupervised Optical Flow Estimation

Xunpei Sun, Wenwei Lin, Yi Chang +1

Unsupervised optical flow methods typically lack reliable uncertainty estimation, limiting their robustness and interpretability. We propose UFlow, the first recurrent unsupe…

cs.CV2026

Adapting Depth Anything to Adverse Imaging Conditions with Events

Shihan Peng, Yuyang Xiong, Hanyu Zhou +5

Robust depth estimation under dynamic and adverse lighting conditions is essential for robotic systems. Currently, depth foundation models, such as Depth Anything, achieve great su…

cs.CV2025

VKFPos: A Learning-Based Monocular Positioning with Variational Bayesian Extended Kalman Filter Integration

Jian-Yu Chen, Yi-Ru Chen, Yin-Qiao Chang +3

This paper addresses the challenges in learning-based monocular positioning by proposing VKFPos, a novel approach that integrates Absolute Pose Regression (APR) and Relative Pose R…

cs.CV2024

Learning Monocular Depth from Events via Egomotion Compensation

Haitao Meng, Chonghao Zhong, Sheng Tang +6

Event cameras are neuromorphically inspired sensors that sparsely and asynchronously report brightness changes. Their unique characteristics of high temporal resolution, high dynam…