TensoRF-张量辐射场论文笔记
TensoRF-张量辐射场论文笔记_什度学习的博客-CSDN博客
注释代码: https://github.com/xunull/read-TensoRF
官方源码：https://github.com/apchenstu/TensoRF
目录
README
Install environment
配置清华园
ERROR: No matching distribution found for cv2
Terminal打开失败
Quick Start
For pretrained checkpoints and results please see:
Rendering
Extracting mesh
Training with your own data
张量基础知识
编辑
参考论文
一个多维张量在线CP分解的高效算法
基于张量分析的欠定混合矩阵估计算法
代码
总结优化算法收敛性证明的两类方法 https://zhuanlan.zhihu.com/p/299473551
README
Install environment
conda create -n TensoRF python=3.8
conda activate TensoRF
pip install torch torchvision
pip install tqdm scikit-image opencv-python configargparse lpips imageio-ffmpeg kornia lpips tensorboard配置清华园
pip config set global.index-url https://pypi.tuna.tsinghua.edu.cn/simple
ERROR: No matching distribution found for cv2
pip install -i https://pypi.tuna.tsinghua.edu.cn/simple/ opencv-python
Terminal打开失败
Quick Start
The training script is in train.py, to train a TensoRF:
python train.py --config configs/lego.txt
we provide a few examples in the configuration folder, please note:
dataset_name, choices = ['blender', 'llff', 'nsvf', 'tankstemple'];
shadingMode, choices = ['MLP_Fea', 'SH'];
model_name, choices = ['TensorVMSplit', 'TensorCP'], corresponding to the VM and CP decomposition. You need to uncomment the last a few rows of the configuration file if you want to training with the TensorCP model；
n_lamb_sigma and n_lamb_sh are string type refer to the basis number of density and appearance along XYZ dimension;
N_voxel_init and N_voxel_final control the resolution of matrix and vector;
N_vis and vis_every control the visualization during training;
You need to set --render_test 1/--render_path 1 if you want to render testing views or path after training.
More options refer to the opt.py.
For pretrained checkpoints and results please see:
https://1drv.ms/u/s!Ard0t_p4QWIMgQ2qSEAs7MUk8hVw?e=dc6hBm
Rendering
python train.py --config configs/lego.txt --ckpt path/to/your/checkpoint --render_only 1 --render_test 1
You can just simply pass --render_only 1 and --ckpt path/to/your/checkpoint to render images from a pre-trained checkpoint. You may also need to specify what you want to render, like --render_test 1, --render_train 1 or --render_path 1. The rendering results are located in your checkpoint folder.
Extracting mesh
You can also export the mesh by passing --export_mesh 1:
python train.py --config configs/lego.txt --ckpt path/to/your/checkpoint --export_mesh 1
Note: Please re-train the model and don't use the pretrained checkpoints provided by us for mesh extraction, because some render parameters has changed.
Training with your own data
We provide two options for training on your own image set:
- Following the instructions in the NSVF repo, then set the dataset_name to 'tankstemple'.
- Calibrating images with the script from NGP:
python dataLoader/colmap2nerf.py --colmap_matcher exhaustive --run_colmap, then adjust the datadir inconfigs/your_own_data.txt. Please check thescene_bboxandnear_farif you get abnormal results.
张量基础知识
摘自-稀疏高阶张量CP分解
几何意义
- 两个向量构成的平面的法向量
- 构件三维坐标系
- 外积在数值上等于两个向量组成平行四边形的面积
参考论文
一个多维张量在线CP分解的高效算法
基于张量分析的欠定混合矩阵估计算法
代码
TensoRF-张量辐射场论文笔记相关推荐
- 论文笔记：Autoregressive Tensor Factorizationfor Spatio-temporal Predictions
0 摘要 张量因子tensor factorization分解方法在时空数据分析领域很受欢迎,因为它们能够处理多种类型的时空数据,处理缺失值,并提供计算效率高的参数估计程序. 然而,现有的张量因子分解 ...
- 神经稀疏体素场论文笔记
论文地址:https://proceedings.neurips.cc/paper/2020/file/b4b758962f17808746e9bb832a6fa4b8-Paper.pdf Githu ...
- 论文笔记 -- Communication Lower Bound in Convolution Accelerators 卷积加速器中的通信下界
论文笔记 – Communication Lower Bound in Convolution Accelerators 卷积加速器中的通信下界 @(论文笔记) 文章目录 论文笔记 -- Commun ...
- 论文笔记目录（ver2.0）
1 时间序列 1.1 时间序列预测 论文名称 来源 主要内容 论文笔记:DCRNN (Diffusion Convolutional Recurrent Neural Network: Data-Dr ...
- Collaborative Spatiotemporal Feature Learning for Video Action Recognition 论文笔记
论文笔记 1 引子 在本文中,我们提出了一种新颖的协作时空(CoST)特征学习操作,它与权重共享共同学习时空特征. 给定3D体积视频张量,我们通过从不同角度观看它们,将其展平为三组2D图像. ...
- 论文笔记【A Comprehensive Study of Deep Video Action Recognition】
论文链接:A Comprehensive Study of Deep Video Action Recognition 目录 A Comprehensive Study of Deep Video A ...
- 《CalliGAN: Style and Structure-aware Chinese Calligraphy Character Generator》论文笔记
关于<CalliGAN: Style and Structure-aware Chinese Calligraphy Character Generator>的论文笔记. 原文:Calli ...
- ST-Resnet 论文笔记
ST-Resnet 论文笔记 摘要 人群流量预测对交通管理和公共安全具有重要意义,同时也受到跨区域交通.事件.天气等复杂因素的影响,具有很大的挑战性.我们提出了一种基于深度学习的方法,称为ST-Res ...
- 论文笔记（十二）：Particle Filter Networks: End-to-End Probabilistic Localization From Visual Observations
Particle Filter Networks: End-to-End Probabilistic Localization From Visual Observations 文章概括 摘要 1. ...
最新文章
- python编程初学者指南pdf-Python物理建模初学者指南
- Linuxamp;nbsp;shell中的竖线（|）——…
- windows下用QTwebkit解析html
- Linux yum 命令
- 浏览器缓存机制学习总结
- react实现svg实线、虚线、方形进度条
- linux 提供多用户telnet,linux系统telnet命令怎么用
- python脚本在linux上运行的两种方式_python脚本当作Linux中的服务启动实现方法
- ubuntu怎么切换到root用户,切换到root账号方法
- 解决配置linux环境每次重新连接都需要bash ~/.bashrc的问题
- About static contructor API changes in cocos2d-...
- Selenium基于Python 进行 web 自动化测试
- Mac上有没有好用的WiFi无线网络管理工具？看这里
- 《工业设计史》 第三章：18世纪的设计与商业
- C语言考试题目（一）
- 静态单赋值(一)—gcc中的支配树
- 电子邮箱地址是什么？如何找回电子邮箱的地址呢？
- QQ群—取消对某人的屏蔽
- xy苹果助手未受信任_重要通知：苹果APP紧急修复！
- Fastjson漏洞详情