Showing cs.CVShow all
3 papers · 1 filter
cs.CV2026
SciFlow: Semantic Cross Interference for Self-Supervised Optical Flow Domain Generalization
Jamie Menjay Lin, Jisoo Jeong, Hong Cai +2
Motions of objects and scenes carry essential intelligence in video understanding, offering rich cues for interpreting dynamic settings and interactions. Due to the cost and scarci…
cs.CV2025
Improving Optical Flow and Stereo Depth Estimation by Leveraging Uncertainty-Based Learning Difficulties
Jisoo Jeong, Hong Cai, Jamie Menjay Lin +1
Conventional training for optical flow and stereo depth models typically employs a uniform loss function across all pixels. However, this one-size-fits-all approach often overlooks…
cs.CV2024
SciFlow: Empowering Lightweight Optical Flow Models with Self-Cleaning Iterations
Jamie Menjay Lin, Jisoo Jeong, Hong Cai +3
Optical flow estimation is crucial to a variety of vision tasks. Despite substantial recent advancements, achieving real-time on-device optical flow estimation remains a complex ch…