PaddleHub
tsdf-fusion-python
Our great sponsors
| PaddleHub | tsdf-fusion-python | |
|---|---|---|
| 9 | 2 | |
| 12,501 | 1,087 | |
| 0.7% | - | |
| 1.9 | 0.0 | |
| 6 months ago | about 1 year ago | |
| Python | Python | |
| Apache License 2.0 | BSD 2-clause "Simplified" License |
Stars - the number of stars that a project has on GitHub. Growth - month over month growth in stars.
Activity is a relative number indicating how actively a project is being developed. Recent commits have higher weight than older ones.
For example, an activity of 9.0 indicates that a project is amongst the top 10% of the most actively developed projects that we are tracking.
PaddleHub
-
Where are all the multi-modal models?
China: All of the ERNIE 260B cross-modal stuff.
-
[R] ERNIE-ViLG 2.0: Improving Text-to-Image Diffusion Model with Knowledge-Enhanced Mixture-of-Denoising-Experts + Gradio Demo
Hmm, is the code published? The thing on github just makes requests to a remote server.
-
PaddleHub ERNIE-ViLG
PaddleHub has many interesting model, I have starred it. https://github.com/PaddlePaddle/PaddleHub
-
[R] ERNIE-ViLG, a state-of-the-art text-to-image model that generates images from Chinese text
Was someone able to find out how big the model is and what hardware you need to run it? That info seems to be missing here.
- Baidu ERNIE-ViLG, output comparable to Stable Diffusion, better in anime
-
ERNIE-ViLG, a state-of-the-art text-to-image model that generates images from Chinese text
note this is an updated version, more info here (in chinese): https://github.com/PaddlePaddle/PaddleHub/tree/develop/modules/image/text_to_image/ernie_vilg
-
A text-to-image web app for ERNIE-ViLG is available, with output at 1024x1024 pixels. Example: "a beautiful chipmunk iceskating" (translated to Simplified Chinese by Google Translate). Links are in a comment.
GitHub repo.
-
[P] PaddleHub: An awesome and easy-to-use pre-trained models toolkit
code：https://github.com/PaddlePaddle/PaddleHub
tsdf-fusion-python
-
TSDF integration with disparity maps?
i found this https://github.com/andyzeng/tsdf-fusion-python but it uses depth maps in mm which is not what i need
-
From Azure Kinect To Hololens2
First, I would suggest looking into https://github.com/andyzeng/tsdf-fusion-python and it’s parent project https://github.com/andyzeng/3dmatch-toolbox as they are pretty good KinectFusion implementations that are under active development and support the Azure Kinect v4.
What are some alternatives?
HDR-Multi-Tool - A graphical user interface for parsing HDR10+ and Dolby Vision
tinysfm - Structure From Motion in 50 lines using OpenCV
spleeter - Deezer source separation library including pretrained models.
Meshroom - 3D Reconstruction Software
allennlp - An open-source NLP research library, built on PyTorch.
caer - High-performance Vision library in Python. Scale your research, not boilerplate.
stanford-tensorflow-tutorials - This repository contains code examples for the Stanford's course: TensorFlow for Deep Learning Research.
quanfima - Quanfima (Quantitative Analysis of Fibrous Materials)
deepdrive - Deepdrive is a simulator that allows anyone with a PC to push the state-of-the-art in self-driving
CPPE-Dataset - Code for our paper CPPE - 5 (Medical Personal Protective Equipment), a new challenging object detection dataset
best-of-ml-python - 🏆 A ranked list of awesome machine learning Python libraries. Updated weekly.
consistent_depth - We estimate dense, flicker-free, geometrically consistent depth from monocular video, for example hand-held cell phone video.