Comments (3)
Hi @apchenstu, I tried to disable distance_scale
and density_shift
during training. Namely, I set distance_scale = 1
and density_shift = 0
. After 30k-iter training, this gives me test PSNR of 33.93 on the Lego scene, which is quite inferior to the 36.46 reported in the paper.
May I know whether you mind sharing some intuition why we need such a scale and shift during training to boost the performance? Thanks a lot.
@w-hc , I think it somehow requires to also change density_shift
if you disable distance_scale
. I also encounter issues if I do not change density_shift
, i.e., all alpha values are nearly zeros for all voxels.
from tensorf.
Hi, thanks! It's equivalent to mod with distance_scale and adjusts the thresholds in building the binary volume or marching cude
from tensorf.
Hi, could you explain that why not applying distance_scale during training would lead to divergence ?
from tensorf.
Related Issues (20)
- Use on unbounded scenes? HOT 1
- Problem training on own blender dataset HOT 2
- Problem on replicating LLFF results HOT 1
- Question aboout training with depth supervision
- question about distance_scale HOT 1
- About hyperparameter near_far HOT 1
- May I ask which result data did you use in papers?
- Test PSNR is higher than train PSNR.
- custom data results suffer from floaters HOT 2
- Results with Ignatius not reproducible due to problematic intrinsics file in data HOT 2
- Different logic to compute nSamples in two different places
- Question about weights
- activation function problem (math.)
- Question regarding depth map computation in volume rendering
- Shape of AlphaGridMask is transposed
- Some question about the outer product between the vector and the plane
- Issues in indoor scene
- Coordinate system used by TensoRF as opposed to that of NeRF and instant-ngp
- implement the "render_path" operation on the Blender dataset
- the link of pretrained checkpoints and results failed
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 tensorf.