3 accepted papers
Existing methods for human motion control in video generation typically rely on either 2D poses or explicit 3D parametric models (e.g., SMPL) as control signals. However, 2D poses rigidly bind motion to the driving viewpoint, precluding novel-view synthesis. Explicit 3D models, though structurally i
Automatic polyp segmentation from colonoscopy videos is a critical task for the development of computer-aided screening and diagnosis systems. However, accurate and real-time video polyp segmentation (VPS) is a very challenging task due to low contrast between background and polyps and frame-to-fram…
"We propose a novel model (VP-SAM) adapted from segment anything model (SAM) for video polyp segmentation (VPS), which is a challenging task due to (1) the low contrast between polyps and background and (2) the large frame-to-frame variations of polyp size, position, and shape. Our aim is to take ad…