Comments (4)
Inverse rendering with natural envmap lighting is a very challenging problem. Usually in literature, people make simplified assumptions to make this problem more tractable, for example: 1) model direct illumination only: PhySG, nvdiffrec; 2) fixed geometry: NeILF, InvRender. These simplified assumptions sacrifices quality though. The good thing with photometric images is that lighting are controlled to minimize shadows in captured images, and to simplify the evaluation of rendering equation.
from iron.
Yes, this codebase only expects photometric images, as we have hard-coded a point-light-based renderer:
Line 15 in 8e9a7c1
from iron.
Thanks for the reply. Do you have any idea how to extend it to common capture scenes?
from iron.
Thanks for the cues! help a lot
from iron.
Related Issues (20)
- Exporting materials HOT 3
- Test data HOT 2
- About BRDF HOT 4
- result mesh is not good HOT 3
- How to train/test on my own dataset HOT 30
- Exporting materials HOT 1
- Cuda out of memory HOT 6
- About GGX Renderer HOT 1
- Poor results for metal materials HOT 1
- Low level of details for synthetic dragon HOT 6
- importing model into blender HOT 1
- The question about the edge gradient problem existed in IDR HOT 2
- Poor results in Superman HOT 2
- Is this a bug in the GGX renderer?
- Parameters to improve volumetric fitting for complex object ?
- Render synthetic data: The property "alpha" has the wrong type
- I use the default config, but the reault is too bad HOT 1
- Learning Specular and Roughness fails and produces a strange phenomenon HOT 5
- About preprocessing pipeline HOT 5
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 iron.