JanySunny

you-get

:arrow_double_down: Dumb downloader that scrapes the web

vit-pytorch

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

pytorch-grad-cam

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

vision_transformer

sam

SAM: Sharpness-Aware Minimization (PyTorch)

FCRN-DepthPrediction

Deeper Depth Prediction with Fully Convolutional Residual Networks (FCRN)

F3Net

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

boundary-iou-api

Boundary IoU API (Beta version)

equirectangular-toolbox

Handy tool for equirectangular images

SPH3D-GCN

Spherical Kernel for Efficient Graph Convolution on 3D Point Clouds

Perspective-and-Equirectangular

A tool to transfer Perspective between Equirectangular

pytorch-CAM

Class Activation Mapping written in PyTorch.

Deep-learning-Survey-for-Omnidirectional-vision

LDF

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

360tools

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

eval-co-sod

PyTorch-Based Evaluation Tool for Co-Saliency Detection

lie-transformer-pytorch

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

Trans4PASS

Repository of Trans4PASS (accepted to CVPR2022)

Tangent-Images

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

Discriminative-Feature-Alignment

Discriminative Feature Alignment for Unsupervised Domain Adaptation

lie-transformer

LieTransformer: Equivariant Self-Attention for Lie Groups

V-CNN

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

omnieval

PAV-SOD

Panoramic audiovisual salient object segmentation

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

swscnn

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

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**!

AutoEquiv

Group Equivariant Linear Maps

PDO-eConv-pytorch

twoisprime.github.io

Computer Vision Experiments