We propose a new cascaded architecture for novel view synthesis, called RGBD-Net, which consists of two core components: a hierarchical depth regression network and a depth-aware generator network. The former one predicts depth maps of the target views by using adaptive depth scaling, while the latter one leverages the predicted depths and renders spatially and temporally consistent target images. In the experimental evaluation on standard datasets, RGBD-Net not only outperforms the state-of-the-art by a clear margin, but it also generalizes well to new scenes without per-scene optimization. Moreover, we show that RGBD-Net can be optionally trained without depth supervision while still retaining high-quality rendering. Thanks to the depth regression network, RGBD-Net can be also used for creating dense 3D point clouds that are more accurate than those produced by some state-of-the-art multi-view stereo methods.

Nguyen Phong, Karnewar Animesh, Huynh Lam, Rahtu Esa, Matas Jiri, Heikkilä Janne

A4 Article in conference proceedings

2021 International Conference on 3D Vision (3DV)

P. Nguyen, A. Karnewar, L. Huynh, E. Rahtu, J. Matas and J. Heikkila, "RGBD-Net: Predicting Color and Depth Images for Novel Views Synthesis," 2021 International Conference on 3D Vision (3DV), 2021, pp. 1095-1105, doi: 10.1109/3DV53792.2021.00117

https://doi.org/10.1109/3DV53792.2021.00117 http://urn.fi/urn:nbn:fi-fe2022032124245