HoHoNet
360 analyzer
A PyTorch implementation of a 360-degree indoor depth estimation and room layout analysis system using latent horizontal features.
"HoHoNet: 360 Indoor Holistic Understanding with Latent Horizontal Features" official pytorch implementation.
108 stars
6 watching
24 forks
Language: Jupyter Notebook
last commit: almost 2 years ago 360-photocomputer-visioncvpr2021depth-estimationhohonetroom-layoutsemantic-segmentation
Related projects:
| Repository | Description | Stars |
|---|---|---|
| sunset1995/horizonnet | A PyTorch implementation of a deep learning model for learning room layouts from 360 photos and providing tools for layout analysis and data augmentation. | 325 |
| sunset1995/panoplane360 | A Python framework for reconstructing 3D indoor panoramas from single images using divide and conquer methods | 52 |
 zhijieshen-bjtu/dopnet | Estimates room layouts from indoor panoramic images by disentangling orthogonal planes and accounting for cross-scale distortion | 48 |
 joshua049/stereo-360-layout | An implementation of stereo 360 layout based on computer vision and machine learning techniques. | 13 |
 clementpinard/sfmlearner-pytorch | This codebase provides a PyTorch implementation of an unsupervised depth and ego-motion learning system from video data. | 1,019 |
| clementpinard/depthnet | A PyTorch implementation of a depth estimation network trained on the Still Box dataset | 119 |
 cfernandezlab/360-scene-understanding | Tools and methods for working with 360 panoramic images to understand their layout and geometry. | 46 |
 starrah/dmh-net | A deep learning framework for estimating 3D room layouts from cubemaps of panoramic images using the Deep Manhattan Hough Transform. | 50 |
 thuyngch/human-segmentation-pytorch | An open source implementation of deep learning-based human segmentation models using PyTorch | 558 |
 xingyizhou/pytorch-pose-hg-3d | A PyTorch implementation of a 3D human pose estimation algorithm using weak supervision. | 613 |
 prbonn/depth_clustering | A fast and robust algorithm to segment 3D point clouds generated by Velodyne sensors into objects. | 1,210 |
 mks0601/3dmppe_posenet_release | A PyTorch implementation of a deep learning model for 3D multi-person pose estimation from a single RGB image | 824 |
 wxywhu/srdensenet-pytorch | A PyTorch implementation of an image super-resolution model based on dense skip connections. | 119 |
 chengzhag/deeppanocontext | A PyTorch-based framework for 3D scene understanding with holistic context graph and relation-based optimization in panoramic images | 89 |
 potterhsu/svhnclassifier-pytorch | A PyTorch implementation of multi-digit number recognition from street view imagery using deep convolutional neural networks | 200 |