8 papers
DepthART: Scaling Foundation Monocular Depth to Tiny Models
Feng Xue, Wu Chen, Mingshuai Zhao +7
Recent geometric foundation models (e.g., Metric3D, Depth Anything and UniDepth) have substantially improved monocular depth estimation (MDE) in both cross-scene generalization and…
The Fourth Monocular Depth Estimation Challenge
Anton Obukhov, Matteo Poggi, Fabio Tosi +54
This paper presents the results of the fourth edition of the Monocular Depth Estimation Challenge (MDEC), which focuses on zero-shot generalization to the SYNS-Patches benchmark, a…
MARF: Multiscale Adaptive-switch Random Forest for Leg Detection with 2D Laser Scanners
Tianxi Wang, Feng Xue, Yu Zhou +1
For the 2D laser-based tasks, e.g., people detection and people tracking, leg detection is usually the first step. Thus, it carries great weight in determining the performance of p…
Monocular Depth Distribution Alignment with Low Computation
Fei Sheng, Feng Xue, Yicong Chang +2
The performance of monocular depth estimation generally depends on the amount of parameters and computational cost. It leads to a large accuracy contrast between light-weight netwo…
Fast Road Segmentation via Uncertainty-aware Symmetric Network
Yicong Chang, Feng Xue, Fei Sheng +2
The high performance of RGB-D based road segmentation methods contrasts with their rare application in commercial autonomous driving, which is owing to two reasons: 1) the prior me…
Boundary-induced and scene-aggregated network for monocular depth prediction
Feng Xue, Junfeng Cao, Yu Zhou +3
Monocular depth prediction is an important task in scene understanding. It aims to predict the dense depth of a single RGB image. With the development of deep learning, the perform…