当前位置:网站首页>3D content generation based on nerf
3D content generation based on nerf
2022-07-07 12:45:00 【Nismilesucc】
source : Deep Blue College 《 be based on NeRF 3D content generation 》 Zhang Kai
3D content
Generate from pictures 3D content 【 Labor takes time 、 energy 】 => Automatically generate by computer-aided means
picture : It's very easy to get => Anti rendering Generate 3D content
Computer graphics : How to generate high-quality rendered images
Computer vision : Given picture => Anti rendering generates 3D content needed in computer graphics 【 Can change the light , Insert objects and so on 】
The three elements of anti rendering
1. Shape representation
Triangle Mesh、Point Cloud、Occupancy field、Signed distance filed
Different shape representations may determine the difficulty of solving the problem 【 Different optimization methods 】
2. appearance
The left side represents the material and light separately 【 Ideal situation , You can change the light , Edit material , But it's very difficult to understand ( It involves the rendering process in graphics )】, On the right, pack the material and light together 【 Can't edit well , Put the object in a new environment and observe its appearance ,】
Anti rendering is relative to 3D reconstruction , The key is differentiable,2D->3D->2D
3D reconstruction is a special case of inverse rendering , 3D reconstruction was not focus Rendering quality .
3. Rendering process 【 Optimize 】
Ray tracing rendering: Track the propagation of light , Pass through each in the image pixel The process of weighted summation of light direction color distribution => Get the color of pixels
NeRF
Right picture : The quality of depth map is very high
Soft Shape: Like fog , A little bit appears in every part of the space , Unlike solid objects, they only occupy a small part of space .
Success factors :
1. Shape representation 【 Soft shape representation ( Foggy )】
2. appearance 【 Materials and light 】
3. Rendering process 【 Functions are all differentiable 】
The geometric details on the right may not be good enough 【NeRF shortcoming 】
The previous work with neural network is not good enough => Hard representation is selected (eg. Triangle Mesh)
Reasons for the success of selecting soft shapes :
shortcoming : Every point in the light predict Color =>Expensive
=》 Prove the validity of soft shape , Better rendering can still be achieved without neural networks
There is no neural network (evaluation Very slowly ), For every pixel of light, go querry
At the beginning, neural network is introduced to represent the scene :
Another question : Neural networks have special bias, Tends to fit smooth shape=> Introduced a map Y Y Y
Five scenarios :
- 360 No background , Only the prospect
- Only move the camera within a small range
- Panoramic shooting mode
- Take photos casually with your mobile phone in your room 【 Cameras are more irregular 】
- 360in and outforward Scene , Want to rebuild both the foreground and the background
Local or The overall There is one trade off (a) Choose the point on the foreground (b) Divide the points into the foreground and the background
Yes resolution problem
NeRF++
Draw a ball to deal with the foreground and background
such wrapping The property of can well solve the problem of resolution : Space is squeezed
NeRF It has good composition The nature of
NeRF At present, it cannot run on real-time online devices , It can't support editing well .
NeRF The sampling frequency corresponds to pixel size
NeRF Core assumptions : Objects are static
The sawtooth problem occurs when downsampling , It is related to image sampling frequency .
Nyquist frequency problem
边栏推荐
- NGUI-UILabel
- leetcode刷题:二叉树24(二叉树的最近公共祖先)
- Processing strategy of message queue message loss and repeated message sending
- Preorder, inorder and postorder traversal of binary tree
- Static vxlan configuration
- Attack and defense world ----- summary of web knowledge points
- leetcode刷题:二叉树27(删除二叉搜索树中的节点)
- [statistical learning method] learning notes - support vector machine (I)
- 【从 0 开始学微服务】【01】什么是微服务
- Visual stdio 2017 about the environment configuration of opencv4.1
猜你喜欢
On valuation model (II): PE index II - PE band
[pytorch practice] image description -- let neural network read pictures and tell stories
[statistical learning method] learning notes - logistic regression and maximum entropy model
Solutions to cross domain problems
Day-14 common APIs
Charles: four ways to modify the input parameters or return results of the interface
Static routing assignment of network reachable and telent connections
静态Vxlan 配置
ACL 2022 | 序列标注的小样本NER:融合标签语义的双塔BERT模型
Day-16 set
随机推荐
Day-15 common APIs and exception mechanisms
用mysql查询某字段是否有索引
In the small skin panel, use CMD to enter the MySQL command, including the MySQL error unknown variable 'secure_ file_ Priv 'solution (super detailed)
Pule frog small 5D movie equipment | 5D movie dynamic movie experience hall | VR scenic area cinema equipment
What is an esp/msr partition and how to create an esp/msr partition
SQL lab 21~25 summary (subsequent continuous update) (including secondary injection explanation)
Several methods of checking JS to judge empty objects
Is it safe to open an account in Ping An Securities mobile bank?
SQL lab 11~20 summary (subsequent continuous update) contains the solution that Firefox can't catch local packages after 18 levels
Learning and using vscode
sql-lab (54-65)
leetcode刷题:二叉树19(合并二叉树)
【从 0 开始学微服务】【03】初探微服务架构
Configure an encrypted web server
Importance of database security
[Q&A]AttributeError: module ‘signal‘ has no attribute ‘SIGALRM‘
OSPF exercise Report
静态Vxlan 配置
【统计学习方法】学习笔记——提升方法
Epp+dis learning road (2) -- blink! twinkle!