Image Collection
Image collection research focuses on efficiently organizing, analyzing, and synthesizing information from large, often unstructured, visual datasets. Current efforts concentrate on developing algorithms and models, such as neural radiance fields (NeRFs) and 3D Gaussian splatting, that enable tasks like novel view synthesis, 3D reconstruction from sparse or unconstrained images, and semantic clustering guided by natural language. These advancements have significant implications for various fields, including computer vision, digital art, e-commerce, and medical imaging, by improving search, retrieval, and analysis capabilities for massive image collections.
Papers
GenRC: Generative 3D Room Completion from Sparse Image Collections
Ming-Feng Li, Yueh-Feng Ku, Hong-Xuan Yen, Chi Liu, Yu-Lun Liu, Albert Y. C. Chen, Cheng-Hao Kuo, Min Sun
Splatfacto-W: A Nerfstudio Implementation of Gaussian Splatting for Unconstrained Photo Collections
Congrong Xu, Justin Kerr, Angjoo Kanazawa