-
Hanyang University
- Seoul, South Korea
- https://soonminhwang.github.io
Stars
The Atlas Benchmark offers a collection of scripts and functions for evaluating 2D trajectory predictors.
[ITS'21] Human Trajectory Forecasting in Crowds: A Deep Learning Perspective
This repository contains utility scripts for the KITTI-360 dataset.
Taming Transformers for High-Resolution Image Synthesis
Official implementation of the paper: MonoRec: Semi-Supervised Dense Reconstruction in Dynamic Environments from a Single Moving Camera (CVPR 2021)
higher is a pytorch library allowing users to obtain higher order gradients over losses spanning training loops rather than individual training steps.
converts set of point clouds to a video using three.js
PyTorch Implementations for DeeplabV3 and PSPNet
Bounding Box Regression with Uncertainty for Accurate Object Detection (CVPR'19)
''Multispectral Pedestrian Detection via Simultaneous Detection and Segmentation''. BMVC 2018.
Official PyTorch code for "BAM: Bottleneck Attention Module (BMVC2018)" and "CBAM: Convolutional Block Attention Module (ECCV2018)"
Semantic Segmentation Architectures Implemented in PyTorch
Supervisely SDK for Python - convenient way to automate, customize and extend Supervisely Platform for your computer vision task
Pretrained ConvNets for pytorch: NASNet, ResNeXt, ResNet, InceptionV4, InceptionResnetV2, Xception, DPN, etc.
Frustum PointNets for 3D Object Detection from RGB-D Data
A sophisticated scientific image viewer for Linux with OpenGL support and synchronized viewports
A OpenMMLAB toolbox for human pose estimation, skeleton-based action recognition, and action synthesis.
A do-it-yourself thermal imager, compatible with the FLIR Lepton 2.5, 3.1R and 3.5 sensor with Arduino firmware
Online web tool for image annotation (Pascal VOC format used in Image Recognition)
Collection of Super-Resolution models via PyTorch
Pytorch implementation of FlowNet 2.0: Evolution of Optical Flow Estimation with Deep Networks
Open-source simulator for autonomous driving research.
Decoupled Neural Interfaces using Synthetic Gradients for PyTorch
tensorboard for pytorch (and chainer, mxnet, numpy, ...)