3D Computer Vision
3D computer vision focuses on enabling computers to "see" and understand three-dimensional scenes, aiming to reconstruct, analyze, and interact with the world in a way similar to human vision. Current research emphasizes improving the accuracy and efficiency of tasks like camera calibration, object pose estimation (using methods like neural radiance fields and diffusion models), and 3D object detection (leveraging point clouds and multi-view approaches). These advancements are crucial for applications ranging from autonomous driving and robotics to agriculture and structural inspection, driving significant progress in both the theoretical understanding and practical deployment of 3D vision systems.
Papers
Foundation Model-Powered 3D Few-Shot Class Incremental Learning via Training-free Adaptor
Sahar Ahmadi, Ali Cheraghian, Morteza Saberi, Md.Towsif Abir, Hamidreza Dastmalchi, Farookh Hussain, Shafin Rahman
Diffusion-Based Depth Inpainting for Transparent and Reflective Objects
Tianyu Sun, Dingchang Hu, Yixiang Dai, Guijin Wang