lxtGH

video-ttt-release

Awesome-Video-Diffusion

A curated list of recent diffusion models for video generation, editing, restoration, understanding, etc.

kmax-deeplab

a PyTorch re-implementation of ECCV 2022 paper based on Detectron2: k-means mask Transformer.

Prompt-Diffusion

Official PyTorch implementation of the paper "In-Context Learning Unlocked for Diffusion Models"

GPT4RoI

GPT4RoI: Instruction Tuning Large Language Model on Region-of-Interest

StableSR

Exploiting Diffusion Prior for Real-World Image Super-Resolution

LLaVA

[NeurIPS'23 Oral] Visual Instruction Tuning (LLaVA) built towards GPT-4V level capabilities and beyond.

InternLM

Official release of InternLM2 7B and 20B base and chat models. 200K context support

CrossKD

CrossKD: Cross-Head Knowledge Distillation for Dense Object Detection

VoxFormer

Official PyTorch implementation of VoxFormer [CVPR 2023 Highlight]

StreamPETR

[ICCV 2023] StreamPETR: Exploring Object-Centric Temporal Modeling for Efficient Multi-View 3D Object Detection

UniAD

[CVPR 2023 Best Paper] Planning-oriented Autonomous Driving

Point-In-Context

[NeurIPS2023] Implementation of the paper: Explore In-Context Learning for 3D Point Cloud Understanding

OmniObject3D

[ CVPR 2023 Award Candidate ] OmniObject3D: Large-Vocabulary 3D Object Dataset for Realistic Perception, Reconstruction and Generation

ULIP

InternLM-techreport

hiera

Hiera: A fast, powerful, and simple hierarchical vision transformer.

Voyager

An Open-Ended Embodied Agent with Large Language Models

ContextDET

Contextual Object Detection with Multimodal Large Language Models

InternVideo

Video Foundation Models & Data for Multimodal Understanding

InternGPT

InternGPT (iGPT) is an open source demo platform where you can easily showcase your AI models. Now it supports DragGAN, ChatGPT, ImageBind, multimodal chat like GPT-4, SAM, interactive image editing, etc. Try it at igpt.opengvlab.com (支持DragGAN、ChatGPT、ImageBind、SAM的在线Demo系统)

DragGAN

Official Code for DragGAN (SIGGRAPH 2023)

LLaMA-Adapter

[ICLR 2024] Fine-tuning LLaMA to follow Instructions within 1 Hour and 1.2M Parameters

learning_research

本人的科研经验

ImageBind

ImageBind One Embedding Space to Bind Them All

open_flamingo

An open-source framework for training large multimodal models.

SegmentAnyRGBD

Segment Any RGBD

Multimodal-GPT

Multimodal-GPT

eqlv2

The official implementation of Equalization Loss v1 & v2 (CVPR 2020, 2021) based on MMDetection. https://arxiv.org/abs/2012.08548 https://arxiv.org/abs/2003.05176

BasicSR

Open Source Image and Video Restoration Toolbox for Super-resolution, Denoise, Deblurring, etc. Currently, it includes EDSR, RCAN, SRResNet, SRGAN, ESRGAN, EDVR, BasicVSR, SwinIR, ECBSR, etc. Also support StyleGAN2, DFDNet.