AI RESEARCH

PacTure: Efficient PBR Texture Generation on Packed Views with Visual Autoregressive Models

arXiv CS.CV

ArXi:2505.22394v2 Announce Type: replace We present PacTure, a novel framework for generating physically-based rendering (PBR) material textures for an untextured 3D mesh from a text description. Existing 2D generation-based texturing approaches either generate textures sequentially from different views, resulting in long inference times and globally inconsistent textures, or adopt multi-view generation with cross-view attention to enhance global consistency, which, however, limits the resolution for each view. In response to these weaknesses, we first.