Depth-supervised NeRF: Fewer Views and Faster Training for Free 链接:https://openaccess.thecvf.com/content/CVPR2022/papers/Deng_Depth-Supervised_NeRF_Fewer_Views_and_Faster_Training_for_Free_CVPR_2022_paper.pdf What: Nerf 常见的问题是:如果输入的训练图像不足(nerf往往要100多张各个角度训练图像) ...
Target: 引入深度约束达到两个效果,1)使用少量图片即能收敛到Origianl NERF 100+张图片的效果 2)训练速度得到提高 这篇文章的切入点是用fewer views作为NERF的input来完成场景的生成且能够有不错的效果,它的实验结果证明引入depth-supervised的方法能够在仅用几张图片作为输入的情况下,就能够达到和Original NERF(arxiv...
NeRF (Depth-supervised Neural Radiance Fields), a loss for learning radiance fields that takes advantage of readily-available depth supervision. We leverage the fact that current NeRF pipelines require images with known camera poses that are typically estimated by running structure-from-motion (SFM)....
Our work is based on the state-of-the-art framework VolSDF, which models 3D scenes by signed distance functions (SDFs), since this is more applicable for surface reconstruction compared to the standard volumetric representation in vanilla NeRFs. For evaluatio...
Depth-supervised NeRF: Fewer Views and Faster Training for Free CVPR, 2022 Kangle Deng1,Andrew Liu2,Jun-Yan Zhu1,Deva Ramanan1,3, 1CMU,2Google,3Argo AI We propose DS-NeRF (Depth-supervised Neural Radiance Fields), a model for learning neural radiance fields that takes advantage of depth ...
Depth-supervised nerf: Fewer views and faster train- ing for free, 2021. [7] Arno Knapitsch, Jaesik Park, Qian-Yi Zhou, and Vladlen Koltun. Tanks and temples: Benchmarking large-scale scene reconstruction. ACM Transactions on Graphics, 36(4), 2017. [8] Lingjie Liu, Jiatao Gu, Ky...
Depth-supervised nerf: Fewer views and faster train- ing for free. In CVPR, 2022. 3 [8] Alexey Dosovitskiy, Lucas Beyer, Alexander Kolesnikov, Dirk Weissenborn, Xiaohua Zhai, Thomas Unterthiner, Mostafa Dehghani, Matthias Minderer, Georg Heigold, Syl- vain Gelly, Jakob Uszkoreit,...
Deng, K., Liu, A., Zhu, J.Y., Ramanan, D.: Depth-supervised nerf: fewer views and faster training for free. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 12882–12891 (2022) Google Scholar Furukawa, Y., Ponce, J.: Accurate, dense, ...
在上一篇介绍引入深度优化NERF的文章(DS-NERF) 中,以colmap的稀疏点云分布(假设为高斯分布)为目标,使ray termination distribution逼近真实的点云分布,学习的过程用color loss 加 KL散度的 depth loss加以约束。这个idea直观且简单,但也有明显的上限约束,即当点云的深度不够准确时,depth的优化可能起不到预想的作用...
Deng, K.; Liu, A.; Zhu, J.Y.; Ramanan, D. Depth-supervised nerf: Fewer views and faster training for free. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, New Orleans, LA, USA, 18–24 June 2022; pp. 12882–12891. [Google Scholar] ...