Learning Robust Image-Based Rendering on Sparse Scene Geometry via Depth Completion

Yuqi Sun, Shili Zhou, Ri Cheng, Weimin Tan, Bo Yan, Lang Fu; Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2022, pp. 7813-7823

Recent image-based rendering (IBR) methods usually adopt plenty of views to reconstruct dense scene geometry. However, the number of available views is limited in practice. When only few views are provided, the performance of these methods drops off significantly, as the scene geometry becomes sparse as well. Therefore, in this paper, we propose Sparse-IBRNet (SIBRNet) to perform robust IBR on sparse scene geometry by depth completion. The SIBRNet has two stages, geometry recovery (GR) stage and light blending (LB) stage. Specifically, GR stage takes sparse depth map and RGB as input to predict dense depth map by exploiting the correlation between two modals. As inaccuracy of the complete depth map may cause projection biases in the warping process, LB stage first uses a bias-corrected module (BCM) to rectify deviations, and then aggregates modified features from different views to render a novel view. Extensive experimental results demonstrate that our method performs best on sparse scene geometry than recent IBR methods, and it can generate better or comparable results as well when the geometric information is dense.