Total3DUnderstanding
Scene reconstruction
An implementation of a 3D scene reconstruction method from a single image using computer vision and machine learning techniques
Implementation of CVPR'20 Oral: Total3DUnderstanding: Joint Layout, Object Pose and Mesh Reconstruction for Indoor Scenes from a Single Image
423 stars
14 watching
50 forks
Language: Python
last commit: 8 months ago cvpr2020pytorchscene-reconstructionscene-understanding
Related projects:
| Repository | Description | Stars |
|---|---|---|
| gap-lab-cuhk-sz/instpifu | This project aims to develop a method for high-fidelity single-view holistic reconstruction of indoor scenes from a single image. | 106 |
 svip-lab/planarreconstruction | A PyTorch implementation of a deep learning-based approach to piece-wise planar 3D reconstruction from single images. | 364 |
 sunset1995/panoplane360 | A Python framework for reconstructing 3D indoor panoramas from single images using divide and conquer methods | 52 |
 3dv-casia/polyroom | A deep learning-based system designed to reconstruct floor plans from raw point cloud data | 27 |
 hongwenzhang/pymaf | Reconstructs human 3D models from monocular images using a feedback loop to improve pose and shape estimation | 597 |
 unclearness/vacancy | Reconstructs 3D models from 2D silhouettes and camera parameters | 65 |
 hoffsupes/structured-light-laser-stripe-reconstruction | Automatically reconstructs 3D depth information from images of a laser stripe on an object | 45 |
 germain-hug/structured-light-depth-acquisition | A Matlab implementation of a 3D reconstruction algorithm using structured light depth acquisition | 70 |
 zouchuhang/layoutnet | A deep learning implementation of a 3D room layout reconstruction method from a single RGB image | 419 |
 autonomousvision/differentiable_volumetric_rendering | A system for generating 3D meshes from input images using learned implicit representations | 805 |
 xgtu/2dasl | Provides code and tools for 3D face reconstruction and alignment from a single image using self-supervised learning. | 467 |
 ashual/scene_generation | A PyTorch implementation of a deep learning-based method for generating interactive scenes with specified object attributes and relations | 187 |
 cyang0515/noncuboidroom | A deep learning project that aims to reconstruct 3D room layouts from single RGB images | 103 |
 mit-spark/kimera-semantics | Tools and methods for real-time 3D reconstruction from 2D data in robotics and computer vision | 651 |
 cdoersch/vae_tutorial | An open-source implementation of Variational Autoencoders and Conditional Variational Autoencoders for image reconstruction tasks | 503 |