Stars
[CVPR-2023] Primitive Generation and Semantic-related Alignment for Universal Zero-Shot Segmentation
[NeurIPS 2023] Official implementation of the paper "Segment Everything Everywhere All at Once"
Implementation of the paper Text Augmented Spatial Aware Zero-shot Referring Image Segmentation (Findings of EMNLP 2023)
[CVPR 2025] Hybrid Global-Local Representation with Augmented Spatial Guidance for Zero-Shot Referring Image Segmentation
Simple Finetuning Starter Code for Segment Anything
Grounded SAM: Marrying Grounding DINO with Segment Anything & Stable Diffusion & Recognize Anything - Automatically Detect , Segment and Generate Anything
The repository provides code for running inference with the SegmentAnything Model (SAM), links for downloading the trained model checkpoints, and example notebooks that show how to use the model.
Our project proposes a multi-domain HDR reconstruction model based on inverse RAW generation, which restores intrinsic scene information by simulating the inverse of the camera's RAW-to-LDR pipelin…
Pretrained DeepLabv3 and DeepLabv3+ for Pascal VOC & Cityscapes
[NeurlPS2024] One-Step Effective Diffusion Network for Real-World Image Super-Resolution
A faster pytorch implementation of faster r-cnn
[ICML 2024 Oral] A framework for society simulation that supports complex simulation, for example: multi-scene.
ChatArena (or Chat Arena) is a Multi-Agent Language Game Environments for LLMs. The goal is to develop communication and collaboration capabilities of AIs.
Tools to automatically explore annotated dataset, create statistics and optionally create COCO styled JSONs from txt or XML files.
Creating a Tone Mapper plus Object detector that tone maps HDR images to LDR images, optimized for object detection.
Implementation of paper - YOLOv7: Trainable bag-of-freebies sets new state-of-the-art for real-time object detectors
Repo for the paper "Intrinsic Single-Image HDR Reconstruction" (ECCV 2024)
HDR-CNF: Single-Image High Dynamic Range Imaging based on Conditional Normalizing Flows
A collection of HDR imaging papers.
High Dynamic Range Imaging via Visual Attention Modules
Learning to See in the Dark. CVPR 2018
[CVPR 2020] Single-Image HDR Reconstruction by Learning to Reverse the Camera Pipeline
This repository contains datasets and baselines for benchmarking Chinese text recognition.
[CVPR2024] Diffusion-based Blind Text Image Super-Resolution (Official)
Designing a Practical Degradation Model for Deep Blind Image Super-Resolution (ICCV, 2021) (PyTorch) - We released the training code!
Real-ESRGAN aims at developing Practical Algorithms for General Image/Video Restoration.
Real-CE: A Benchmark for Chinese-English Scene Text Image Super-resolution (ICCV2023)