Abstract | ||
---|---|---|
While NeRF [28] has shown great success for neural reconstruction and rendering, its limited MLP capacity and long per-scene optimization times make it challenging to model large-scale indoor scenes. In contrast, classical 3D reconstruction methods can handle large-scale scenes but do not produce realistic renderings. We propose NeRFusion, a method that combines the advantages of NeRF and TSDF-based fusion techniques to achieve efficient large-scale reconstruction and photo-realistic rendering. We process the input image sequence to predict per-frame local radiance fields via direct network inference. These are then fused using a novel recurrent neural network that incrementally reconstructs a global, sparse scene representation in real-time at 22 fps. This global volume can be further fine-tuned to boost rendering quality. We demonstrate that NeR-Fusionachieves state-of-the-art quality on both large-scale indoor and small-scale object scenes, with substantially faster reconstruction than NeRF and other recent methods. 1 1 https://jetd1.github.io/NeRFusion-Web/ |
Year | DOI | Venue |
---|---|---|
2022 | 10.1109/CVPR52688.2022.00537 | IEEE Conference on Computer Vision and Pattern Recognition |
Keywords | DocType | Volume |
3D from multi-view and sensors, Image and video synthesis and generation | Conference | 2022 |
Issue | Citations | PageRank |
1 | 0 | 0.34 |
References | Authors | |
0 | 5 |
Name | Order | Citations | PageRank |
---|---|---|---|
Xiaoshuai Zhang | 1 | 9 | 2.20 |
Sai Bi | 2 | 63 | 5.28 |
Kalyan Sunkavalli | 3 | 500 | 31.75 |
Hao Su | 4 | 7343 | 302.07 |
Zexiang Xu | 5 | 101 | 10.17 |