The field of computer vision is fueled by the remarkable progress in self-supervised learning. At the forefront of this revolution is DINOv2, a cutting-edge self-supervised vision transformer ...
April 24, 2025 5 Comments
Depth Pro: The Sharp Monocular Metric Depth Estimation from Apple Explanation and Applications
January 21, 2025 Leave a Comment
Depth Pro, is an foundational zero shot metric depth estimation model from Apple ML, nails at creating high resolution, sharp monocular metric depth maps in less than a second. Depth Pro achieves SOTA ...
Sapiens: Foundation for Human Vision Models by Meta
September 24, 2024 Leave a Comment
Sapiens, a family of foundational Human Vision Models by Rawal et al., from Meta, achieves state-of-the-art results for human centric tasks like 2D pose estimation, body-part segmentation, depth ...