Comments (2)
kylesargent
commented on August 24, 2024
Hi,
The eval script is kind of entangled with internal Google infra so I can't release it without some more work. But, I have attached a txt file which contains the scenes used for co3d evaluation.
co3d (2).txt. Maybe that's helpful to you.
Keep in mind that in the main paper we only evaluate on co3d for ablation (not comparing with other methods) and we use a custom split for re10k, co3d, and acid, which I attached. The main evals are for DTU and MipNeRF-360 (for which eval scripts are already provided).
from zeronvs.
kylesargent
commented on August 24, 2024
There are a lot of GitHub issues regarding how to set up training for the 2D diffusion model repo (which is still under construction) so hopefully in another couple weeks I can complete the code release soon and address all of them (including getting the eval scripts open-sourced).
from zeronvs.
Related Issues (20)
- I ran the prediction with launch_inference.sh in test mode and the model was released by your pre-trained model here. Still can't get the test result
- How do I turn SDS anchoring on?
- Cuda out of memory during inference
- How can I use zeronvs-diffusion (feed-forward model) directly without SDS distillation? HOT 5
- How can I get the dataset urls for zeronvs-diffusion training? HOT 3
- the value of `quantile_scale_blend` in `model.params.conditioning_config` HOT 2
- The actual value of `compute_nearplane_quantile` in zeronvs_diffusion when training on CO3D and Re10K? HOT 3
- About the focus_point_fn HOT 2
- How to download colmap depth from Realestate 10K? HOT 1
- Help for running ZeroNVS on custom images
- Question on RealEstate10k for PixelNeRF style implementation.
- ModuleNotFoundError: No module named 'ldm' HOT 1
- I still can not reproduce the result? Is anyone achieve it?
- Cannot install tinycudann
- xformer no longer works with torch2.0.1
- That's a great work! But I cannot reproduce the results in my device. HOT 3
- Cannot reproduce test result HOT 4
- out of memory HOT 2
- Generate novel views with 6dof+1 parameterization 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 zeronvs.