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 Chen, Cheng-Hao Kuo, Min Sun ;

"Sparse RGBD scene completion is a challenging task especially when considering consistent textures and geometries throughout the entire scene. Different from existing solutions that rely on human-designed text prompts or predefined camera trajectories, we propose , an automated training-free pipeline to complete a room-scale 3D mesh with high-fidelity textures. To achieve this, we first project the sparse RGBD images to a highly incomplete 3D mesh. Instead of iteratively generating novel views to fill in the void, we utilized our proposed E-Diffusion to generate a view-consistent panoramic RGBD image which ensures global geometry and appearance consistency. Furthermore, we maintain the input-output scene stylistic consistency through textual inversion to replace human-designed text prompts. To bridge the domain gap among datasets, E-Diffusion leverages models trained on large-scale datasets to generate diverse appearances. outperforms state-of-the-art methods under most appearance and geometric metrics on ScanNet and ARKitScenes datasets, even though is not trained on these datasets nor using predefined camera trajectories. Project page: https://minfenli.github. io/GenRC/ Diffusion models"