SOTA Semantic Segmentation Models in PyTorch

Official implementation of the T-RO paper "DALI: Domain Adaptive LiDAR Object Detection via Distribution-level and Instance-level Pseudo Label Denoising"

ScAR: Scaling Adversarial Robustness for LiDAR Object Detection, IROS2023 paper

Python library for loading and using triangular meshes.

This is a Python + OpenCV implementation of the Vanishing Point algorithm by Xiaohu Lu et al. - http://xiaohulugo.github.io/papers/Vanishing_Point_Detection_WACV2017.pdf

Pretrain, finetune ANY AI model of ANY size on multiple GPUs, TPUs with zero code changes.

pytorch structural similarity (SSIM) loss

set sensors on an autonomous agents(a vehicle) in carla and collect albedo, depth, reflection vector, semantic data and rgb image

Official GitHub repository for Argoverse dataset

An invertible generative model that converts color images into grayscale variant such that the original color is still restorable. [SIGGRAPH Asia 2018]

Automatic topology constructing and global stitching optimization for large-scale unordered UAV aerial images. [Pattern Recognition 2017]

📝Awesome and classical image retrieval papers

ezSIFT: An easy-to-use standalone SIFT library written in C/C++

The framework for uncertatitnty computation for SfM pipelines.

Fuse multiple depth frames into a TSDF voxel volume.

A list of papers and datasets about point cloud analysis (processing)

Collecting papers about domain translations.

A Pytorch implementation of DeepCrack and RoadNet projects.

A really fast C++ library for Delaunay triangulation of 2D points

Detect and recognize faces in videos based on dlib

White Balancing images using CNN network model proposed by Simone Bianco

Improving color consistency across multiple images via global optimization on the color remapping curves. [ICCVW 2017 & ISPRS Journal 2019]

[CVPR 2019 Oral] Multi-Channel Attention Selection GAN with Cascaded Semantic Guidance for Cross-View Image Translation

Easy build for ORB Slam 2 on Windows

Repo for counting stars and contributing. Press F to pay respect to glorious developers.

An "infinite"-resolution and interpretable GAN. It works based on a differentiable photo editing model and reinforcement learning. (ACM Transactions on Graphics, presented at SIGGRAPH 2018)

UNet in pytorch for Kaggle 2018 data science bowl nuclei segmentation

Compute rigid transformation and similarity transformation of 2 point sets