JanySunny

Deep-learning-Survey-for-Omnidirectional-vision

Trans4PASS

Repository of Trans4PASS (accepted to CVPR2022)

you-get

:arrow_double_down: Dumb downloader that scrapes the web

equirectangular-toolbox

Handy tool for equirectangular images

Perspective-and-Equirectangular

A tool to transfer Perspective between Equirectangular

twoisprime.github.io

Computer Vision Experiments

360tools

The 360tools package is software for VR video processing experiments. The software includes both 360 video conversion and quality metrics functionality

PAV-SOD

Panoramic audiovisual salient object segmentation

eval-co-sod

PyTorch-Based Evaluation Tool for Co-Saliency Detection

SODEvalToolkit

A More Powerful Evaluation Toolbox for Salient Object Detection, I can use **6 key metrics** to evaluate (max F-measure, mean F-measure, weighted F-measure, MAE, S-measure, and E-measure), **draw**, and **export to excel**!

LDF

Codes for the CVPR2020 paper "Label Decoupling Framework for Salient Object Detection"

F3Net

Codes for the AAAI 2020 paper "F3Net: Fusion, Feedback and Focus for Salient Object Detection"

sam

SAM: Sharpness-Aware Minimization (PyTorch)

pytorch-CAM

Class Activation Mapping written in PyTorch.

pytorch-grad-cam

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

lie-transformer

LieTransformer: Equivariant Self-Attention for Lie Groups

lie-transformer-pytorch

Implementation of Lie Transformer, Equivariant Self-Attention, in Pytorch

g_selfatt

Code repository for the paper "Group Equivariant Stand-Alone Self Attention For Vision" published at ICLR 2021. https://openreview.net/forum?id=JkfYjnOEo6M

PDO-eConv-pytorch

FCRN-DepthPrediction

Deeper Depth Prediction with Fully Convolutional Residual Networks (FCRN)

Discriminative-Feature-Alignment

Discriminative Feature Alignment for Unsupervised Domain Adaptation

vit-pytorch

Implementation of Vision Transformer, a simple way to achieve SOTA in vision classification with only a single transformer encoder, in Pytorch

vision_transformer

omnieval

V-CNN

Viewport-based CNN for visual quality assessment on 360° video

swscnn

Demo source code for the paper "Spin-Weighted Spherical CNNs".

Tangent-Images

Official repository for "Tangent Images for Mitigating Spherical Distortion," CVPR 2020

AutoEquiv

Group Equivariant Linear Maps

boundary-iou-api

Boundary IoU API (Beta version)

SPH3D-GCN

Spherical Kernel for Efficient Graph Convolution on 3D Point Clouds