kim0930 Goto Github PK

pixelformer

planarrecon

planercnn

PlaneRCNN detects and reconstructs piece-wise planar surfaces from a single RGB image

pop_up_image

Real-time 3D Scene Layout from a Single Image Using Convolutional Neural Networks

py360convert

Python implementation of convertion between equirectangular, cubemap and perspective. (equirect2cube, cube2equirect, equirect2perspec)

pyslam

Non-linear least-squares SLAM in Python using scipy and numpy. Modelled after Google's Ceres solver.

pytorch-grad-cam

Advanced AI Explainability for computer vision. Support for CNNs, Vision Transformers, Classification, Object detection, Segmentation, Image similarity and more.

pytorch-layoutnet

Pytorch implementation of LayoutNet.

roomlayout3d_randc

semantic-segmentation

SOTA Semantic Segmentation Models in PyTorch

simplerecon

[ECCV 2022] SimpleRecon: 3D Reconstruction Without 3D Convolutions

single_view_metrology

Reconstruction of a 3 dimensional object/scene by computing necessary and sufficient aspects of the affine 3-D geometry of the object/scene in consideration.

sparseplanes

[ICCV 2021 (oral)] Planar Surface Reconstruction from Sparse Views

stella_vslam-openvslam-

This is a unofficial fork of OpenVSLAM (https://github.com/xdspacelab/openvslam)

structure-from-motion

A simplified version of incremental structure from motion to reconstruct the 3D structure of a scene from a sequence of 2D images

structure-from-motion-with-opencv

Exercise structure from motion pipeline with OpenCV.

template2

test

transformers

🤗 Transformers: State-of-the-art Machine Learning for Pytorch, TensorFlow, and JAX.

vanishing-point-detection-and-3d-plane-segmentation

Detecting 3 Orthogonal Vanishing Points + Using Planar Homography for 3D Plane Segmentation

vanishingpoint_houghtransform_gaussiansphere

Official implementation: Deep vanishing point detection: Geometric priors make dataset variations vanish, CVPR'22.

virtualtour

Generic Software for virtual tours. For an implementation see the virtual tour to the inscriptions of the UNESCO World Heritage Site St. Michael in Hildesheim.

yolov4-deepsort

Object tracking implemented with YOLOv4, DeepSort, and TensorFlow.

yolov5_strongsort_osnet

Mult-object tracking and segmentation using YOLOv5 with StrongSORT and OSNet

yolov7-deepsort-tracking

Modular and ready to deploy code to detect and track videos using YOLO-v7 and DeepSORT

zoedepth

Metric depth estimation from a single image