3D Mesh
3D mesh processing focuses on the creation, manipulation, and analysis of three-dimensional surface models represented as interconnected triangles. Current research emphasizes efficient mesh generation from various sources, including single images, point clouds, and text descriptions, often employing deep learning architectures like transformers, diffusion models, and graph neural networks. These advancements are driving progress in diverse fields, including computer graphics, robotics, and architecture, by enabling faster and more realistic 3D model creation and manipulation for applications such as virtual reality, 3D printing, and automated scene understanding. Improved evaluation metrics are also being developed to better align with human perception of mesh quality.
Papers
MeshVPR: Citywide Visual Place Recognition Using 3D Meshes
Gabriele Berton, Lorenz Junglas, Riccardo Zaccone, Thomas Pollok, Barbara Caputo, Carlo Masone
RoomTex: Texturing Compositional Indoor Scenes via Iterative Inpainting
Qi Wang, Ruijie Lu, Xudong Xu, Jingbo Wang, Michael Yu Wang, Bo Dai, Gang Zeng, Dan Xu