zju3dv / gcasp Goto Github PK
View Code? Open in Web Editor NEW[CoRL 2022] Generative Category-Level Shape and Pose Estimation with Semantic Primitives
License: MIT License
[CoRL 2022] Generative Category-Level Shape and Pose Estimation with Semantic Primitives
License: MIT License
I'm very impressed with your work! Can you provide some rough results about time consuming?
If possible, pose estimation part and mesh reconstruction part separately. Thanks a lot.
I used the pre-trained weights and pre-trained semantic primitive weights provided by the source code for verification. The results on the Real dataset are basically consistent with the original paper, but the IoU50 and IoU75 indicators on the CAMERA dataset did not match the requirements mentioned in the text. What is the reason for this?
Hi, I'm wondering if the mesh files are contained in the result generate by eval.py, or I need to find ways to generate them manually?
Also, I met a problem when I try to generate result by instruction provided in README, which the eval.py only generate empty folder, could you kindly tell me where is the problem?
Thank you!
Hi, thank you for sharing, but i have the question about how the data_lists/ is generated?
Thank you for sharing,I want to replace the 3dgcn module, is this idea feasible?
Hey I was testing the reconstruction quality of the byproduct reconstruction. The meshes of the other objects look good to me except for the Can class, which always gives out tiny shapes.
I think the pose and scale are correctly applied to transform mesh from canonical space to camera space, as the other objects look very reasonable. I suspect there are some problems with the pre-trained DualSDF-weight, as I observe that during shape optimization in the optimize_shape_ransac
function, the decoded shape from the feature is always tiny.
could you kindly see what is going on with the mesh reconstruction?
Thank you!
Hi, Thanks for this nice work.
Could you provide pre-trained weights?
Thank you!
A declarative, efficient, and flexible JavaScript library for building user interfaces.
🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
An Open Source Machine Learning Framework for Everyone
The Web framework for perfectionists with deadlines.
A PHP framework for web artisans
Bring data to life with SVG, Canvas and HTML. 📊📈🎉
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
Some thing interesting about web. New door for the world.
A server is a program made to process requests and deliver data to clients.
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
Some thing interesting about visualization, use data art
Some thing interesting about game, make everyone happy.
We are working to build community through open source technology. NB: members must have two-factor auth.
Open source projects and samples from Microsoft.
Google ❤️ Open Source for everyone.
Alibaba Open Source for everyone
Data-Driven Documents codes.
China tencent open source team.