planerecover

Plane recovery

A computer vision project that trains a neural network to recover 3D planes from a single image

[ECCV'18] Recovering 3D Planes from a Single Image via Convolutional Neural Networks

GitHub

96 stars
5 watching
14 forks
Language: Python
last commit: over 2 years ago

Related projects:

Repository Description Stars
sjingjia/planerectr A unified query learning approach to recover 3D planes from a single view image 24
icetttb/nopesac A deep learning-based method for reconstructing 3D scenes from sparse views of planes. 65
icetttb/planetr3d An implementation of a deep learning-based method for 3D plane recovery from images. 93
zhou13/shapeunity Develops a method to reconstruct 3D wireframe models from a single image using deep learning 69
eryixie/planerecnet An implementation of a deep learning model for instance segmentation and monocular depth estimation. 79
yi-ming-qian/interplane A framework for learning pairwise inter-plane relations to reconstruct piecewise planar surfaces from 3D scans. 40
sunset1995/panoplane360 A Python framework for reconstructing 3D indoor panoramas from single images using divide and conquer methods 52
ibm/max-inception-resnet-v2 An image classification model using a third-generation deep residual network. 28
atiyo/deep_image_prior Reconstructs images using untrained neural networks to manipulate and transform existing images 215
algolzw/daclip-uir This project controls vision-language models to restore degraded images in various environments and conditions. 662
flanggut/smvs Reconstructs 3D scenes from multiple images using a shading-aware multi-view stereo approach 252
csbdeep/csbdeep Toolbox for improving digital images taken with fluorescence microscopy using deep learning algorithms 285
filipradenovic/cnnimageretrieval This MATLAB toolbox trains and tests convolutional neural networks for image retrieval tasks, including fine-tuning and supervised whitening. 189
yunishi3/3d-fcr-alphagan This project aims to develop a generative model for 3D multi-object scenes using a novel network architecture inspired by auto-encoding and generative adversarial networks. 103
charlesq34/frustum-pointnets A deep learning framework for 3D object detection from RGB-D data 1,592