Comments (1)
Thanks for your interest! You might be onto something, but it is not immediately clear to me how you propose to separate the foreground. In your example, the floor area at the very bottom is closer to the camera than the bench pixels, which is why naive thresholding won't work. Also, I see no simple way to perform connected components analysis, as the bottom of the bench legs has the same depth values as the floor underneath. All in all, this calls for some learned approach. I will close the ticket for now, but feel free to continue the discussion in this ticket -- we are always on the lookout for cool applications!
from marigold.
Related Issues (20)
- Clipping is Removing Valuable Depth Estimation Values, Resulting in Squished Depth Maps HOT 2
- How to write depthmap in pfm HOT 2
- Can this algorithm be used to obtain real-world distance to an object? HOT 2
- Out of memory when training with RTX4090, seeking guidance on training details HOT 13
- Question on the output HOT 4
- About Recovering the Depth with Metirc. HOT 1
- Try to convert depth maps to normal maps HOT 1
- Why the inference sometimes outputs a depth map and sometimes outputs a parallax map? HOT 1
- why the paper was named Marigold? HOT 3
- "--seed" not making results reproducible HOT 1
- LCM support HOT 1
- Would you be willing to share the code used for your training process? HOT 6
- Regarding the Stochastic Nature of the Stable Diffusion v2 VAE's Encoder HOT 1
- The main difference between this paper and other density visual prediction methods utilizing the diffusion model HOT 1
- Request: Make model available in Onnx and .pt format. HOT 2
- Request: Need models in onnx and .pt format (not just .bin and .config) HOT 6
- About evaluation protocol HOT 1
- Stable Diffusion fine-tuning problem HOT 5
- Different results from huggingface demo and github repo 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 marigold.