Comments (6)
Albedo looks fine but occlusion looks dirty and ambiguous.
The occlusion threshold can be set --occlusion 0.25
when you conduct baking.py.
from gs-ir.
Same here.
The albedo and roughness have some results though I think it is still wrong if you compute the psnr on albedo which is only around 20.
I follow this training process:
python train.py
-m outputs/lego/
-s lego
--iterations 30000
--eval
python baking.py
-m outputs/lego/
--checkpoint outputs/lego/chkpnt30000.pth
--bound 1.5
--occlu_res 128
--occlusion 0.25
python train.py
-m outputs/lego/
-s lego/
--start_checkpoint outputs/lego/chkpnt30000.pth
--iterations 35000
--eval
--gamma
--indirect
from gs-ir.
Well, the occlusion is so strange (dirty), and I've checked the code.
I think that you can set the sample_rays
here as 1
and check the occlusion (This may be a mistake when I release the code):
Line 16 in e8d979e
Since I am recovering ambient occlusion from spherical harmonics, this already includes hemisphere pre-convolution, so there is no need to perform importance sampling.
GS-IR/gs-ir/src/occlusion_kernel.cu
Lines 184 to 237 in e8d979e
from gs-ir.
Well, the occlusion is so strange (dirty), and I've checked the code. I think that you can set the
sample_rays
here as1
and check the occlusion (This may be a mistake when I release the code):Line 16 in e8d979e
Since I am recovering ambient occlusion from spherical harmonics, this already includes hemisphere pre-convolution, so there is no need to perform importance sampling.
GS-IR/gs-ir/src/occlusion_kernel.cu
Lines 184 to 237 in e8d979e
Hi, thanks for you reply. I wonder what do you mean "occlusion", I think this output is roughness map?
Could you be more specific about how to visualize the occlusion? Thanks!
from gs-ir.
You can directly save the occlusion as an image.
Line 170 in e8d979e
from gs-ir.
Well, the occlusion is so strange (dirty), and I've checked the code. I think that you can set the
sample_rays
here as1
and check the occlusion (This may be a mistake when I release the code):Line 16 in e8d979e
Since I am recovering ambient occlusion from spherical harmonics, this already includes hemisphere pre-convolution, so there is no need to perform importance sampling.
GS-IR/gs-ir/src/occlusion_kernel.cu
Lines 184 to 237 in e8d979e
你好,我更改了sample_rays int = 1然后重新跑了一下,渲染出来的图片,很奇怪,请问这样子正常吗
from gs-ir.
Related Issues (20)
- Missing files in submodule HOT 2
- ERROR:name 'SummaryWriter' is not defined HOT 2
- RE in stage 2 HOT 1
- Weird relighting result HOT 8
- backward for depthToNormal HOT 1
- Inatallation and reproducing results HOT 3
- Implementation details about point lighting HOT 4
- I cannot install the diff rendering submodule HOT 5
- How to precompute brdf_lut HOT 1
- Brigthness during relighting seems off in the garden scene HOT 6
- How to crop the scene HOT 1
- some Relighting steps problems HOT 2
- Why add ray norm to depth map before building cubemap when baking? HOT 1
- Strange occlusion result
- What is the result?
- How are the relighting results evaluated?
- Environment and irradiance results do not match the ones shown in Figure 2 for Mip-NeRF360 garden scene
- shadow_map.py error
- Problems with Demo Implementation
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 gs-ir.