smplify-x
Image-to-3D capture framework
A software framework for capturing 3D human body and facial features from single images using machine learning models.
Expressive Body Capture: 3D Hands, Face, and Body from a Single Image
2k stars
66 watching
340 forks
Language: Python
last commit: 9 months ago
Linked from 1 awesome list
amrzv/awesome-colab-notebooksRelated projects:
| Repository | Description | Stars |
|---|---|---|
 hongwenzhang/pymaf | Reconstructs human 3D models from monocular images using a feedback loop to improve pose and shape estimation | 596 |
 robot-perception-group/airpose | A deep learning framework for multi-view fusion network-based 3D human motion capture system | 52 |
 vita-epfl/monoloco | A library for 3D vision tasks using 2D keypoints | 428 |
 caizhongang/smpler-x | An implementation of an expressive human pose and shape estimation system using deep learning techniques | 1,006 |
 cdoersch/vae_tutorial | An open-source implementation of Variational Autoencoders and Conditional Variational Autoencoders for image reconstruction tasks | 502 |
| hongwenzhang/pymaf-x | An open-source software project that enables the recovery of full-body 3D human models from monocular images. | 224 |
 wenchao-m/how-3d | Performs 3D wireframe perception from a single image | 37 |
 blurstudio/cross3d | Provides a consistent interface to multiple 3D computer graphics application APIs. | 138 |
 flanggut/smvs | Reconstructs 3D scenes from multiple images using a shading-aware multi-view stereo approach | 252 |
 autonomousvision/differentiable_volumetric_rendering | A system for generating 3D meshes from input images using learned implicit representations | 804 |
 zhou13/shapeunity | Develops a method to reconstruct 3D wireframe models from a single image using deep learning | 69 |
 mks0601/3dmppe_posenet_release | A PyTorch implementation of a deep learning model for 3D multi-person pose estimation from a single RGB image | 821 |
 sunset1995/panoplane360 | A Python framework for reconstructing 3D indoor panoramas from single images using divide and conquer methods | 52 |
| hongwenzhang/danet-densepose2smpl | This repository provides software tools and pre-trained models for estimating 3D human shape and pose from dense body parts | 233 |
 zhourax/vega | Develops a multimodal task and dataset to assess vision-language models' ability to handle interleaved image-text inputs. | 33 |