Feynman1999

HAIR

The Official Implementation for "HAIR: Hypernetworks-based All-in-One Image Restoration".

llama.cpp

LLM inference in C/C++

MeshAnythingV2

From anything to mesh like human artists. Official impl. of "MeshAnything V2: Artist-Created Mesh Generation With Adjacent Mesh Tokenization"

EMA-VFI

[CVPR 2023] Extracting Motion and Appearance via Inter-Frame Attention for Efficient Video Frame Interpolatio

Kolors

Kolors Team

Awesome-RWKV-in-Vision

A curated list of papers on the applications of RWKV in computer vision.

flux

Official inference repo for FLUX.1 models

DMD2

SEAL

ICLR 2024 (Spotlight) - SEAL: A Framework for Systematic Evaluation of Real-World Super-Resolution

d3d12book

Sample code for the book "Introduction to 3D Game Programming with DirectX 12"

Diffusion-RWKV

Scaling RWKV-Like Architectures for Diffusion Models

ONNX-RAFT-Optical-Flow-Estimation

Python scripts for performing optical flow estimation using the RAFT model in ONNX

OpticalFlow_Visualization

Python optical flow visualization following Baker et al. (ICCV 2007) as used by the MPI-Sintel challenge

Awesome-Unity-Shader

:boat: 关于炫酷的Unity3D Shader | About Cool Unity3D Shaders

ActionRoguelike

Third-person Action Roguelike made in Unreal Engine C++. Project for Unreal Engine C++ Course & Stanford University

aitoolkit

Give a brain to your game's NPCs

OSEDiff

KBNet

KBNet: Kernel Basis Network for Image Restoration

RQ-VQA

Enhancing Blind Video Quality Assessment with Rich Quality-aware Features

SEA-RAFT

[ECCV2024 Oral] SEA-RAFT: Simple, Efficient, Accurate RAFT for Optical Flow

AIGCDetectBaseline

AIGCDetectBaseline

CPVT

SRFormer

Official code for "SRFormer: Permuted Self-Attention for Single Image Super-Resolution" (ICCV 2023) and SRFormerV2

rope-vit

[ECCV 2024] Official PyTorch implementation of RoPE-ViT "Rotary Position Embedding for Vision Transformer"

ERealSR-DGPNet

Efficient Real-world Image Super-Resolution Via Adaptive Directional Gradient Convolution

LLaVA-pp

🔥🔥 LLaVA++: Extending LLaVA with Phi-3 and LLaMA-3 (LLaVA LLaMA-3, LLaVA Phi-3)

improved-diffusion

Release for Improved Denoising Diffusion Probabilistic Models

SPAN

Swift Parameter-free Attention Network for Efficient Super-Resolution

Phantom

repository for dreamoving-phantom https://www.modelscope.cn/studios/vigen/DreaMoving_Phantom/summary. DreaMoving-Phantom is a general and automatic image enhancement and super resolution framework.

distrifuser

[CVPR 2024 Highlight] DistriFusion: Distributed Parallel Inference for High-Resolution Diffusion Models