2 papers
cs.CV2026
LoLep: Single-View View Synthesis with Locally-Learned Planes and Self-Attention Occlusion Inference
Cong Wang, Yu-Ping Wang, Dinesh Manocha
We propose a novel method, LoLep, which regresses Locally-Learned planes from a single RGB image to represent scenes accurately, thus generating better novel views. Without the dep…
cs.CV2026
MotionHint: Self-Supervised Monocular Visual Odometry with Motion Constraints
Cong Wang, Yu-Ping Wang, Dinesh Manocha
We present a novel self-supervised algorithm named MotionHint for monocular visual odometry (VO) that takes motion constraints into account. A key aspect of our approach is to use…