3 papers
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.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…
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…