Dong-hwi Kim's Projects
Open Source Image and Video Restoration Toolbox for Super-resolution, Denoise, Deblurring, etc. Currently, it includes EDSR, RCAN, SRResNet, SRGAN, ESRGAN, EDVR, etc. Also support StyleGAN2, DFDNet.
Principled Method for Digital Image Retargeting: Implementation of a principled method for digital image retargeting using the “Patch-Based Bidirectional Similarity” measure. The project includes two parts: the first consists in a method for image retargeting based on a course-to-fine algorithm as proposed by publication Simakov et al. CVPR’08. The
CVPR2023 : VL-SAT: Visual-Linguistic Semantics Assisted Training for 3D Semantic Scene Graph Prediction in Point Cloud
PyTorch implements "Enhanced Deep Residual Networks for Single Image Super-Resolution"
GAN의 튜토리얼
Arxiv2022 - Activating More Pixels in Image Super-Resolution Transformer
Official code for the paper "InGAN: Capturing and Retargeting the DNA of a Natural Image"
LSUN Dataset Documentation and Demo Code
[ICCV 2023] PyTorch Implementation of "MotionBERT: A Unified Perspective on Learning Human Motion Representations"
변형된 영상의 객체 인식 최적화 연구
Video Retargeting Using Instance Segmentation and Video Inpainting
This code is comparsion PSNR of two images.
Code samples used on cloud.google.com
파이토치를 사용한 CNN 신경망 구성과 MNIST 분류문제 해결
A fast Python implementation of Seam Carving for Content-Aware Image Resizing.
A matlab implementation of "Optimized Scale-and-Stretch for Image Resizing"
Pruning the SRGAN model
Super Resolution Network Feature Compression
This repo contains source code and materials for the TEmporally COherent GAN SIGGRAPH project.
A PyTorch Reimplementation of TecoGAN: Temporally Coherent GAN for Video Super-Resolution
Content-Aware Image Retargeting.