Name: Universe24
Type: User
Company: Urban Robotics Lab. (Room No. 3239, E3-2 Bldg.) School of Electrical Engineering KAIST (Korea Advanced Institute of Science and Technology)
Bio: Domain generalization, computer vision researcher
Location: 291 Daehak-ro Yuseong-gu Daejeon 34141 Republic of Korea
Universe24's Projects
PyTorch implementation for All-In-One Image Restoration for Unknown Corruption (AirNet) (CVPR 2022)
Generating 3D Adversarial Point Clouds
4D Panoptic Lidar Segmentation
Official PyTorch implementation of the NeurIPS 2021 paper: Encoding Robustness to Image Style via Adversarial Feature Perturbations.
pip install antialiased-cnns to improve stability and accuracy
AugMix: A Simple Data Processing Method to Improve Robustness and Uncertainty
[ICRA'23] BEVFusion: Multi-Task Multi-Sensor Fusion with Unified Bird's-Eye View Representation
Offical PyTorch implementation of "BEVFusion: A Simple and Robust LiDAR-Camera Fusion Framework"
CubeSLAM: Monocular 3D Object Detection and SLAM
cvl with RGB and LiDAR
YOLOv4 - Neural Networks for Object Detection (Windows and Linux version of Darknet )
Self-Supervised Learning for Domain Adaptation on Point-Clouds
Official page of ERASOR (RA-L'21 with ICRA'21)
This the project folder for the paper `Fusing Event-based and RGB camera for Robust Object Detection in Adverse Conditions'
Official Implementation of 'Fast AutoAugment' in PyTorch.
Unofficial pytorch implementation of Fourier Heat Map proposed in 'A Fourier Perspective on Model Robustness in Computer Vision' [Yin+, NeurIPS2019]
Trained model weights, training and evaluation code from the paper "Increasing the robustness of DNNs against image corruptions by playing the Game of Noise"
Implementation for the paper (CVPR Oral): High Frequency Component Helps Explain the Generalization of Convolutional Neural Networks
CVPR2022 "Beyond Cross-view Image Retrieval: Highly Accurate Vehicle Localization Using Satellite Image"
Pytorch implementation of HorizonNet: Learning Room Layout with 1D Representation and Pano Stretch Data Augmentation.
This is the open source implementation of the CVPR2022 paper "Iterative Deep Homography Estimation"
A Disentangling Invertible Interpretation Network
Python package to corrupt arbitrary images.
ImageNet-R(endition) and DeepAugment
Pytorch implementation of various Knowledge Distillation (KD) methods.
Semantic and Instance Segmentation of LiDAR point clouds for autonomous driving