ScanNet-Layout
Layout estimation
A dataset and evaluation tool for benchmarking 3D room layout estimation from single views.
We introduce the ScanNet-Layout dataset for benchmarking general 3D room layout estimation from single view.
33 stars
5 watching
2 forks
Language: Python
last commit: over 4 years ago 3d-visionaugmented-realitycomputer-visiondeep-learningprojective-geometryroom-layout
Related projects:
Repository | Description | Stars |
---|---|---|
| A deep learning framework for estimating 3D room layouts from multi-view panoramas using stereo vision and fusion techniques. | 3 |
| Estimates room layouts from indoor panoramic images by disentangling orthogonal planes and accounting for cross-scale distortion | 48 |
| Provides annotated 3D layout data for room reconstruction from a single 360° image | 63 |
| A deep learning framework for estimating 3D room layouts from cubemaps of panoramic images using the Deep Manhattan Hough Transform. | 50 |
| 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 |
| An implementation of a 3D layout reconstruction algorithm from a single 360-degree image using PyTorch and machine learning techniques. | 222 |
| A deep learning implementation of a 3D room layout reconstruction method from a single RGB image | 419 |
| A Swift implementation of a mosaic collection view layout inspired by Lightbox's Algorithm | 250 |
| An implementation of a 3D scene reconstruction method from a single image using computer vision and machine learning techniques | 424 |
| A deep learning-based system for detecting wireframe layouts in 2D images of rooms | 72 |
| An optimized graph layout algorithm for visualizing networks in D3 | 50 |
| An implementation of stereo 360 layout based on computer vision and machine learning techniques. | 13 |
| This project develops software for detecting and understanding 3D layouts in dynamic environments. | 23 |
| An architecture and toolset for training deep learning models to perform pixel-level tasks such as image segmentation and surface normal estimation. | 196 |
| Provides algorithms for arranging complex network structures in a visually appealing manner | 275 |