Comments (3)
Hi, thanks for your interests. The CostVolumeInitNet does not require depth actually though I have passed it into the model. You can just implement a new database and return a dummy depth map like np.zeros([h,w],dtype=float32) in get_depth().
from neuray.
Thank you for your reply, which solves my problem. Then the new question is:
- How can I output a depth map when rendering, like the figure15 in your paper;
- I found that on my own dataset, the neuray method will lose some objects. I want to ask which parameters I should modify to improve the image quality?
the neuray results: some objects losed
Thank you very much.
from neuray.
For your new questions:
- I have added an interface to render depth:
Line 195 in fb3188d
Line 202 in fb3188d
Results will be saved indata/render
. - Possible reasons for missing objects: 1) depth range does not include the object. 2) too few images seeing the object so that it cannot be correctly matched to construct the radiance field.
- Possible improvements: The MVSNet is only trained on the DTU dataset and it is fixed during the generalization training for NVS so it is not very accurate for outdoor scenes or the forward-facing scenes according to my experience. 1) I recommend reconstructing the scene by COLMAP and using the DepthInitNet, which performs better. 2) You may finetune the MVSNet in the NVS training, which however may consume lots of GPU memory.
Thank you!
from neuray.
Related Issues (20)
- Is the pose of data world-to-camera parameter, or camera-to-world parameter?
- How to get the accuracy presented in Tab. 1? HOT 2
- 环境问题 HOT 2
- 渲染自定义数据报错 HOT 2
- 渲染自定义数据集的问题
- 自定义数据集问题 HOT 1
- How to apply multi-gpus training? HOT 1
- finished HOT 6
- Cannot download the pre-training model HOT 3
- Cannot download the processed test datasets LLFF. HOT 2
- DTU dataset, colmap depth for DTU training images and colmap depth for forward-facing scenes HOT 2
- Kindly remind that there may be some minor mistakes in 'configs/' folder HOT 1
- Question for the coordinate? HOT 1
- difference of 'pixel_colors_nr' and 'pixel_colors_nr_fine' HOT 2
- Question for the rendering HOT 9
- A question about color c
- Custom scene rendering
- DTU testing dataset
- Why adding a negative sign to the ray direction in NeuRay? HOT 2
- Possible bug in equation (9) HOT 1
Recommend Projects
-
React
A declarative, efficient, and flexible JavaScript library for building user interfaces.
-
Vue.js
🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
-
Typescript
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
-
TensorFlow
An Open Source Machine Learning Framework for Everyone
-
Django
The Web framework for perfectionists with deadlines.
-
Laravel
A PHP framework for web artisans
-
D3
Bring data to life with SVG, Canvas and HTML. 📊📈🎉
-
Recommend Topics
-
javascript
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
-
web
Some thing interesting about web. New door for the world.
-
server
A server is a program made to process requests and deliver data to clients.
-
Machine learning
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
-
Visualization
Some thing interesting about visualization, use data art
-
Game
Some thing interesting about game, make everyone happy.
Recommend Org
-
Facebook
We are working to build community through open source technology. NB: members must have two-factor auth.
-
Microsoft
Open source projects and samples from Microsoft.
-
Google
Google ❤️ Open Source for everyone.
-
Alibaba
Alibaba Open Source for everyone
-
D3
Data-Driven Documents codes.
-
Tencent
China tencent open source team.
from neuray.