Repositories list

• Rex-Omni

  Public

  IDEA-Research/Rex-Omni’s past year of commit activity
  Detect Anything via Next Point Prediction (Based on Qwen2.5-VL-3B)

  object-detectionopen-setmllm

  Jupyter Notebook

  •

  Other

  •71•1.1k•14•0•Updated Jan 10, 2026Jan 10, 2026

• SegDINO3D

  Public

  IDEA-Research/SegDINO3D’s past year of commit activity
  [AAAI 2026] Official implementation of the paper ”SegDINO3D: 3D Instance Segmentation Empowered by Both Image-Level and Object-Level 2D Features“

  Python

  •

  Apache License 2.0

  •0•13•0•0•Updated Jan 8, 2026Jan 8, 2026

• SceneMaker

  Public

  IDEA-Research/SceneMaker’s past year of commit activity
  Implementation of paper "SceneMaker: Open-set 3D Scene Generation with Decoupled De-occlusion and Pose Estimation Model"

  Apache License 2.0

  •1•43•1•0•Updated Jan 1, 2026Jan 1, 2026

• Grounded-SAM-2

  Public

  IDEA-Research/Grounded-SAM-2’s past year of commit activity
  Grounded SAM 2: Ground and Track Anything in Videos with Grounding DINO, Florence-2 and SAM 2

  Jupyter Notebook

  •

  Apache License 2.0

  •366•3.2k•53•3•Updated Nov 11, 2025Nov 11, 2025

• DINO-X-MCP

  Public

  IDEA-Research/DINO-X-MCP’s past year of commit activity
  Official DINO-X Model Context Protocol (MCP) server that empowers LLMs with real-world visual perception through image object detection, localization, and captioning APIs.

  mcpimage-recognitionobject-detection+ 2pose-estimationmcp-server

  TypeScript

  •

  Apache License 2.0

  •10•108•1•1•Updated Oct 28, 2025Oct 28, 2025

• RexSeek

  Public

  IDEA-Research/RexSeek’s past year of commit activity
  [ICCV2025] Referring any person or objects given a natural language description. Code base for RexSeek and HumanRef Benchmark

  detectionmulti-modalopen-set+ 3referringllmvllm

  Python

  •

  Other

  •10•177•0•0•Updated Oct 15, 2025Oct 15, 2025

• ChatRex

  Public

  IDEA-Research/ChatRex’s past year of commit activity
  Code for ChatRex: Taming Multimodal LLM for Joint Perception and Understanding

  detectionvlmmultimodal-deep-learning+ 2llmmllm

  Python

  •

  Other

  •8•210•10•0•Updated Oct 15, 2025Oct 15, 2025

• T-Rex

  Public

  IDEA-Research/T-Rex’s past year of commit activity
  [ECCV2024] API code for T-Rex2: Towards Generic Object Detection via Text-Visual Prompt Synergy

  interactiveobject-detectionopen-set+ 3object-countingtext-promptvisual-prompt

  Python

  •

  Other

  •170•2.6k•14•0•Updated Oct 15, 2025Oct 15, 2025

• detrex

  Public

  IDEA-Research/detrex’s past year of commit activity
  detrex is a research platform for DETR-based object detection, segmentation, pose estimation and other visual recognition tasks.

  pytorchsegmentationobject-detection+ 13pose-estimationdinostate-of-the-artdetadetrdeformable-detrdab-detr+ 6

  Python

  •

  Apache License 2.0

  •242•2.3k•79•4•Updated Sep 11, 2025Sep 11, 2025

• DINO-X-API

  Public

  IDEA-Research/DINO-X-API’s past year of commit activity
  DINO-X: The World's Top-Performing Vision Model for Open-World Object Detection and Understanding

  pose-estimationopen-set-object-detectionvisual-prompt+ 2region-captionopen-set-object-segmentation

  Python

  •

  Apache License 2.0

  •60•1.3k•33•1•Updated Jul 23, 2025Jul 23, 2025

• Rex-Thinker

  Public

  IDEA-Research/Rex-Thinker’s past year of commit activity
  Rex-Thinker: Grounded Object Refering via Chain-of-Thought Reasoning

  object-detectionreferring-expression-comprehensionmllm+ 1grpo

  Python

  •

  Other

  •7•132•9•1•Updated Jun 30, 2025Jun 30, 2025

• 3D-deformable-attention

  Public
  [ICCV 2023] Official implementation of the paper "DFA3D: 3D Deformable Attention For 2D-to-3D Feature Lifting"

  Python

  •

  Other

  •5•178•1•0•Updated Apr 12, 2025Apr 12, 2025

• HandOSweb

  Public

  IDEA-Research/HandOSweb’s past year of commit activity
  HTML

  •0•1•0•0•Updated Mar 19, 2025Mar 19, 2025

• Motion-X

  Public
  [NeurIPS 2023] Official implementation of the paper "Motion-X: A Large-scale 3D Expressive Whole-body Human Motion Dataset"

  Python

  •

  Other

  •24•800•80•0•Updated Mar 3, 2025Mar 3, 2025

• Grounding-DINO-1.5-API

  Public
  Grounding DINO 1.5: IDEA Research's Most Capable Open-World Object Detection Model Series

  open-worldobject-detectionopen-set+ 4zero-shot-object-detectionfoundation-modelopen-vocabulary-detectiongrounding-dino

  Python

  •

  Apache License 2.0

  •44•1.1k•36•2•Updated Jan 21, 2025Jan 21, 2025

• TAPTR

  Public
  [ECCV 2024 & NeurIPS 2024] Official implementation of the paper TAPTR & TAPTRv2 & TAPTRv3

  Other

  •13•270•2•0•Updated Dec 13, 2024Dec 13, 2024

• MotionCLR

  Public
  [Arxiv 2024] MotionCLR: Motion Generation and Training-free Editing via Understanding Attention Mechanisms

  Python

  •

  Other

  •1•14•6•0•Updated Dec 1, 2024Dec 1, 2024

• detrex-storage

  Public

  IDEA-Research/detrex-storage’s past year of commit activity
  Apache License 2.0

  •0•3•0•0•Updated Oct 24, 2024Oct 24, 2024

• DreamWaltz

  Public

  IDEA-Research/DreamWaltz’s past year of commit activity
  [NeurIPS 2023] Official implementation of the paper "DreamWaltz: Make a Scene with Complex 3D Animatable Avatars".

  Python

  •

  Other

  •10•191•1•0•Updated Oct 15, 2024Oct 15, 2024

• MotionLLM

  Public

  IDEA-Research/MotionLLM’s past year of commit activity
  [Arxiv-2024] MotionLLM: Understanding Human Behaviors from Human Motions and Videos

  Python

  •

  Other

  •19•364•8•1•Updated Sep 8, 2024Sep 8, 2024

• Grounded-Segment-Anything

  Public

  IDEA-Research/Grounded-Segment-Anything’s past year of commit activity
  Grounded SAM: Marrying Grounding DINO with Segment Anything & Stable Diffusion & Recognize Anything - Automatically Detect , Segment and Generate Anything

  speechimage-editingcaption+ 5data-generation3d-whole-body-pose-estimationopen-vocabulary-detectionopen-vocabulary-segmentationautomatic-labeling-system

  Jupyter Notebook

  •

  Apache License 2.0

  •1.6k•17k•304•5•Updated Sep 5, 2024Sep 5, 2024

• OSX

  Public

  IDEA-Research/OSX’s past year of commit activity
  [CVPR 2023] Official implementation of the paper "One-Stage 3D Whole-Body Mesh Recovery with Component Aware Transformer"

  human-pose-estimationsmpl-modelsmplx+ 33d-body-recoverywhole-body-pose-estimationcvpr2023

  Python

  •

  MIT License

  •63•767•32•0•Updated Aug 26, 2024Aug 26, 2024

• X-Pose

  Public
  [ECCV 2024] Official implementation of the paper "X-Pose: Detecting Any Keypoints"

  Python

  •

  Other

  •39•774•37•2•Updated Aug 16, 2024Aug 16, 2024

• GroundingDINO

  Public
  [ECCV 2024] Official implementation of the paper "Grounding DINO: Marrying DINO with Grounded Pre-Training for Open-Set Object Detection"

  open-worldobject-detectionvision-language+ 2vision-language-transformeropen-world-detection

  Python

  •

  Apache License 2.0

  •984•9.6k•285•25•Updated Aug 12, 2024Aug 12, 2024

• DINO

  Public
  [ICLR 2023] Official implementation of the paper "DINO: DETR with Improved DeNoising Anchor Boxes for End-to-End Object Detection"

  computer-visiondeep-learningobject-detection

  Python

  •

  Apache License 2.0

  •305•2.7k•149•3•Updated Jul 31, 2024Jul 31, 2024

• awesome-detection-transformer

  Public
  Collect some papers about transformer for detection and segmentation. Awesome Detection Transformer for Computer Vision (CV)

  117•1.4k•7•1•Updated Jul 4, 2024Jul 4, 2024

• HumanTOMATO

  Public

  IDEA-Research/HumanTOMATO’s past year of commit activity
  [ICML 2024] 🍅HumanTOMATO: Text-aligned Whole-body Motion Generation

  motiongenerationgpt+ 4whole-bodysmplxmotion-generationwhole-body-motion

  Python

  •

  Other

  •11•359•20•0•Updated Jun 19, 2024Jun 19, 2024

• TOSS

  Public

  IDEA-Research/TOSS’s past year of commit activity
  [ICLR 2024] Official implementation of the paper "Toss: High-quality text-guided novel view synthesis from a single image"

  open-world3d-generationnovel-view-synthesis

  Python

  •

  Apache License 2.0

  •3•22•1•0•Updated May 5, 2024May 5, 2024

• Stable-DINO

  Public
  [ICCV 2023] Official implementation of the paper "Detection Transformer with Stable Matching"

  transformerobject-detectiondino+ 2detection-transformerdetrex

  Python

  •

  Apache License 2.0

  •7•236•20•0•Updated Apr 29, 2024Apr 29, 2024

• deepdataspace

  Public
  The Go-To Choice for CV Data Visualization, Annotation, and Model Analysis.

  computer-visionmodel-analysislabeling-tool+ 3dataset-visualizationintelligent-annotationcollaborative-annotation

  TypeScript

  •

  Apache License 2.0

  •25•260•6•0•Updated Apr 19, 2024Apr 19, 2024