Comments (1)
Thank you for your thoughtful feedback on our paper. We appreciate your interest in the inference time and implementation specifics. Due to the page constraints of the conference proceedings, we have detailed these aspects in the supplementary material, specifically in Sections E and A (for camera ready version, we may move these parts to the main paper). Regarding inference, we utilize an optimization process for both SMPL and normal, resulting in an overall processing time of approximately 40 seconds when using a single RTX 3090 GPU. In testing scenarios where SMPL ground truth (GT) is available, we bypass the optimization step, significantly reducing the geometry reconstruction time to roughly 0.55 seconds.
from gta.
Related Issues (20)
- Expecting a demo HOT 4
- About the version of pymeshlab HOT 2
- Strange surface of inferenced results HOT 1
- there is no .npy file HOT 1
- about SMPLX model HOT 1
- About PNSR HOT 2
- ViTencoder input HOT 4
- About HGPIFu HOT 2
- get_sampling_geo HOT 1
- SSIM and LIPIS metrics HOT 1
- about training HOT 3
- When will you realease the code? HOT 1
- Question about evaluation. HOT 2
- Texture is vertex coloring or PNG ? HOT 5
- The test results of the pre-trained model are inconsistent with the benchmark HOT 1
- Ask for training code HOT 1
- The test results seems to be inconsistent with the paper HOT 2
- THuman 2.0 evaluation protocol HOT 2
- Question about numbers, evaluation. 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 gta.