[2024 ECCV Workshop] Famba-V: Fast Vision Mamba with Cross-Layer Token Fusion

FusionMamba: Dynamic Feature Enhancement for Multimodal Image Fusion with Mamba

The code of paper "O-Mamba: O-shape State-Space Model for Underwater Image Enhancement"

VFIMamba: Video Frame Interpolation with State Space Models

Ofiicial Implementation for Mamba-ND: Selective State Space Modeling for Multi-Dimensional Data

Improving Mamaba performance on Video Understanding task

Mamba SSM architecture

A paper list of recent mamba efforts for low-level vision.

BJTU论文latex模板的补充包，包含了2024年的诚信声明以及外文翻译模板

A desktop app built with Qt (PySide6) for super resolution with ESRGANs in TensorFlow

This GitHub repository contains a Super Resolution Demo, built using the ncnn inference framework and Qt. The demo is designed to run on various operating systems, including Windows, macOS, and Linux.

使用Vue和Real-ESRGAN的图片放大（清晰化）工具

DCT (discrete cosine transform) functions for pytorch

Animation engine for explanatory math videos

Collaborative Feedback Discriminative Propagation for Video Super-Resolution

[AAAI2024] Omni-Kernel Network for Image Restoration

Seeing the Unseen: A Frequency Prompt Guided Transformer for Image Restoration

Overview of conditional computution and dynamic CNNs for computer vision, with a focus on reducing computational complexity

Local AtrrLocal Attribution Maps (LAM)

局部归因图(Local Attribution Map， LAM)是一个超分辨率重建任务的可解释性工具，旨在找到低分辨率输入图像中对网络超分结果贡献最强烈的像素。LAM 将跟踪模型使用的信息，并在指定超分结果局部区域的前提下，高亮对超分结果贡献最大的像素。

CVPR 2024-Video Super-Resolution Transformer with Masked Inter&Intra-Frame Attention

This project is the official implementation of 'Structured Sparsity Learning for Efficient Video Super-Resolution', CVPR2023

Official repository of "BasicVSR++: Improving Video Super-Resolution with Enhanced Propagation and Alignment"

ATO调试工具