4 papers · 1 filter
OCSplats: Observation Completeness Quantification and Label Noise Separation in 3DGS
Han Ling, Xian Xu, Yinghui Sun +1
3D Gaussian Splatting (3DGS) has become one of the most promising 3D reconstruction technologies. However, label noise in real-world scenarios-such as moving objects, non-Lambertia…
ScaleFlow++: Robust and Accurate Estimation of 3D Motion from Video
Han Ling, Quansen Sun
Perceiving and understanding 3D motion is a core technology in fields such as autonomous driving, robots, and motion prediction. This paper proposes a 3D motion perception method c…
Self-Assessed Generation: Trustworthy Label Generation for Optical Flow and Stereo Matching in Real-world
Han Ling, Yinghui Sun, Quansen Sun +2
A significant challenge facing current optical flow and stereo methods is the difficulty in generalizing them well to the real world. This is mainly due to the high costs required…
ScaleFlow++: Robust and Accurate Estimation of 3D Motion from Video
Han Ling, Yinghui Sun, Quansen Sun +1
Perceiving and understanding 3D motion is a core technology in fields such as autonomous driving, robots, and motion prediction. This paper proposes a 3D motion perception method c…