collaborators

5 papers

cs.CV2026

SynFlow: Scaling Up LiDAR Scene Flow Estimation with Synthetic Data

Qingwen Zhang, Xiaomeng Zhu, Chenhan Jiang +1

Reliable 3D dynamic perception requires models that can anticipate motion beyond predefined categories, yet progress is hindered by the scarcity of dense, high-quality motion annot…

cs.CV2026

TeFlow: Enabling Multi-frame Supervision for Self-Supervised Feed-forward Scene Flow Estimation

Qingwen Zhang, Chenhan Jiang, Xiaomeng Zhu +4

Self-supervised feed-forward methods for scene flow estimation offer real-time efficiency, but their supervision from two-frame point correspondences is unreliable and often breaks…

cs.CV2025

DeltaFlow: An Efficient Multi-frame Scene Flow Estimation Method

Qingwen Zhang, Xiaomeng Zhu, Yushan Zhang +3

Previous dominant methods for scene flow estimation focus mainly on input from two consecutive frames, neglecting valuable information in the temporal domain. While recent trends s…

cs.CV2025

Afford-X: Generalizable and Slim Affordance Reasoning for Task-oriented Manipulation

Xiaomeng Zhu, Yuyang Li, Leiyao Cui +4

Object affordance reasoning, the ability to infer object functionalities based on physical properties, is fundamental for task-oriented planning and activities in both humans and A…

cs.LG2025

AutoScale: Linear Scalarization Guided by Multi-Task Optimization Metrics

Yi Yang, Kei Ikemura, Qingwen Zhang +5

Recent multi-task learning studies suggest that linear scalarization, when using well-chosen fixed task weights, can achieve comparable to or even better performance than complex m…