Stars
[SIGGRAPH Asia 2024, Journal Track] ToonCrafter: Generative Cartoon Interpolation
Tool for visual profiling Core ML models, compatible with both package and compiled versions, including reasons for unsupported operations on the Neural Engine
[ECCV2024] Video Foundation Models & Data for Multimodal Understanding
code for <Compressing Image Super-resolution Network via Model Compression and Knowledge Distillation>
Fast pixelshuffle and pixelshuffle-invert implementations via pytorch.
This is the official testing code of the baseline method presented at the CVPR 2023 NTIRE Real-Time 4K Super-Resolution Challenge. We provide model and pre-trained checkpoints.
Large Kernel Distillation Network for Efficient Single Image Super-Resolution
This repository contains the official implementation of the research paper, "An Improved One millisecond Mobile Backbone".
Core ML tools contain supporting tools for Core ML model conversion, editing, and validation.
Official repository of the paper 'Structure-Aware Flow Generation for Human Body Reshaping' in CVPR 2022
Arxiv - Partial Large Kerenl CNNs for Efficient Super-Resolution
[ECCV 2024 - Oral] HiT-SR: Hierarchical Transformer for Efficient Image Super-Resolution
GUI for upscaling ONNX models with NVIDIA TensorRT and Vapoursynth
neosr is a framework for training real-world single-image super-resolution networks.
Code for Adam-mini: Use Fewer Learning Rates To Gain More https://arxiv.org/abs/2406.16793
All my self trained & released AI upscaling models. After gathering and applying over 600 different upscaling models, I learned how to train my own models, and these are the results.
CVPR2024 - Transcending the Limit of Local Window: Advanced Super-Resolution Transformer with Adaptive Token Dictionary
[ICCV 2021] Focal Frequency Loss for Image Reconstruction and Synthesis
A repository collecting image and video upscaling resources as well as my own super resolution models.
[PG 2023] WaveNet: Wave-Aware Image Enhancement
one summary of diffusion-based image processing, including restoration, enhancement, coding, quality assessment
A node-based image processing GUI aimed at making chaining image processing tasks easy and customizable. Born as an AI upscaling application, chaiNNer has grown into an extremely flexible and power…
A Collection of Papers and Codes for CVPR2024/CVPR2021/CVPR2020 Low Level Vision
Spandrel gives your project support for various PyTorch architectures meant for AI Super-Resolution, restoration, and inpainting. Based on the model support implemented in chaiNNer.
Various scripts, mostly intended to help with model training and dataset creation
Deep learning training framework for image super resolution and restoration.