当前位置:网站首页>[2021]IBRNet: Learning Multi-View Image-Based Rendering Qianqian
[2021]IBRNet: Learning Multi-View Image-Based Rendering Qianqian
2022-07-05 06:17:00 【Dark blue blue blue】
NeRF A big problem is that it can only represent one scene , Therefore, this article proposes a framework for learning multiple scenarios at the same time , And it can be extended to scenes that have not been studied .
This article and NeRF The biggest difference is that the input data does not only have a target perspective , There are also corresponding multi view pictures of the same scene , Therefore, theoretically, it can be directly applied to new scenarios end-to-end .
Model flow :
1. Input the multi view pictures of the same scene into the network ( There is no limit to the number of ), Then use a U-Net To extract each picture (source view) Characteristics of , Features include image color , Camera parameters , Image representation ( Here it can be understood as NeRF Emitting light to the radiation field in , Then save the corresponding light parameters and image features ).
2. Then input the features of each picture in parallel transformer, Used to predict a common color and density . The reason for the common color and density is that the features input from multiple perspectives are the features of the same point in different perspectives by default , So the result is to predict our target perspective (target view) Results at this point .
3. Render the result by volume rendering , Then optimize the network through the reconstruction loss of pixels
4. Another scene , repeat 1~3
remarks : If you keep training with the same scene , In theory, the effect will be better , That's what the paper mentioned finetune The situation of .
Personal understanding : In essence, the model here learns “ How to interpolate ”, Instead of building a radiation field , Therefore, it may not perform well in sparse situations or complex scenes
边栏推荐
- Leetcode-6109: number of people who know secrets
- LeetCode 1200. Minimum absolute difference
- Leetcode-556: the next larger element III
- leetcode-3:无重复字符的最长子串
- 1.13 - RISC/CISC
- Leetcode-9: palindromes
- MIT-6874-Deep Learning in the Life Sciences Week 7
- Multi screen computer screenshots will cut off multiple screens, not only the current screen
- LeetCode 1200.最小绝对差
- Currently clicked button and current mouse coordinates in QT judgment interface
猜你喜欢
Network security skills competition in Secondary Vocational Schools -- a tutorial article on middleware penetration testing in Guangxi regional competition
Simple selection sort of selection sort
Leetcode-6108: decrypt messages
Real time clock (RTC)
SQLMAP使用教程(一)
实时时钟 (RTC)
Operator priority, one catch, no doubt
LeetCode 0108.将有序数组转换为二叉搜索树 - 数组中值为根,中值左右分别为左右子树
LeetCode 0108. Convert an ordered array into a binary search tree - the median of the array is the root, and the left and right of the median are the left and right subtrees respectively
SPI 详解
随机推荐
LVS简介【暂未完成(半成品)】
快速使用Amazon MemoryDB并构建你专属的Redis内存数据库
【LeetCode】Day95-有效的数独&矩阵置零
[rust notes] 14 set (Part 1)
【Rust 笔记】17-并发(上)
TypeScript 基础讲解
LaMDA 不可能觉醒吗?
Real time clock (RTC)
Liunx starts redis
Erreur de connexion Navicat à la base de données Oracle Ora - 28547 ou Ora - 03135
MySQL advanced part 1: triggers
MySQL advanced part 2: MySQL architecture
Navicat连接Oracle数据库报错ORA-28547或ORA-03135
【Rust 笔记】16-输入与输出(上)
JS quickly converts JSON data into URL parameters
多屏电脑截屏会把多屏连着截下来,而不是只截当前屏
[BMZCTF-pwn] ectf-2014 seddit
4. 对象映射 - Mapping.Mapster
1996. number of weak characters in the game
1041 Be Unique