3D Representation

3D representation research focuses on creating effective and efficient computational models of three-dimensional scenes and objects, primarily for applications in computer vision, robotics, and cultural heritage preservation. Current research emphasizes developing robust and generalizable methods using architectures like neural radiance fields (NeRFs), Gaussian splatting, and voxel-based representations, often incorporating self-supervised learning and multi-modal data fusion (e.g., combining images, point clouds, and text). These advancements are driving progress in areas such as autonomous driving, 3D reconstruction from sparse views, and interactive 3D content creation, impacting both scientific understanding and practical applications.