Alternatives and similar repositories for UniRef

Users that are interested in UniRef are comparing it to the libraries listed below

• SHI-Labs / VCoder
  [CVPR 2024] VCoder: Versatile Vision Encoders for Multimodal Large Language Models
  ☆277Updated last year
• berkeley-hipie / HIPIE
  [NeurIPS2023] Code release for "Hierarchical Open-vocabulary Universal Image Segmentation"
  ☆291Updated 4 months ago
• OPPOMKLab / recognize-anything
  Codebase for the Recognize Anything Model (RAM)
  ☆85Updated last year
• bytedance / coconut_cvpr2024
  ☆193Updated 5 months ago
• hustvl / EVF-SAM
  Official code of "EVF-SAM: Early Vision-Language Fusion for Text-Prompted Segment Anything Model"
  ☆476Updated 7 months ago
• xk-huang / segment-caption-anything
  [CVPR 24] The repository provides code for running inference and training for "Segment and Caption Anything" (SCA) , links for downloadin…
  ☆228Updated last year
• Saiyan-World / grounded-segment-any-parts
  Grounded Segment Anything: From Objects to Parts
  ☆416Updated 2 years ago
• WesleyHsieh0806 / TAO-Amodal
  Official Code for Tracking Any Object Amodally
  ☆119Updated last year
• PhyscalX / gradio-image-prompter
  Image Prompter for Gradio
  ☆91Updated last year
• NVlabs / LITA
  ☆186Updated last year
• IDEA-Research / RexSeek
  [ICCV2025] Referring any person or objects given a natural language description. Code base for RexSeek and HumanRef Benchmark
  ☆167Updated last week
• ylqi / Count-Anything
  This method uses Segment Anything and CLIP to ground and count any object that matches a custom text prompt, without requiring any point …
  ☆171Updated 2 years ago
• LLaVA-VL / LLaVA-Interactive-Demo
  LLaVA-Interactive-Demo
  ☆378Updated last year
• RockeyCoss / Prompt-Segment-Anything
  This is an implementation of zero-shot instance segmentation using Segment Anything.
  ☆314Updated 2 years ago
• YuchenLiu98 / COMM
  Pytorch code for paper From CLIP to DINO: Visual Encoders Shout in Multi-modal Large Language Models
  ☆203Updated 9 months ago
• naver-ai / ZIM
  [ICCV 2025, Highlight] ZIM: Zero-Shot Image Matting for Anything
  ☆355Updated last month
• feizc / IEA
  Image Editing Anything
  ☆116Updated 2 years ago
• facebookresearch / VLPart
  [ICCV2023] VLPart: Going Denser with Open-Vocabulary Part Segmentation
  ☆385Updated 2 years ago
• google / imageinwords
  Data release for the ImageInWords (IIW) paper.
  ☆220Updated 11 months ago
• baaivision / tokenize-anything
  [ECCV 2024] Tokenize Anything via Prompting
  ☆596Updated 10 months ago
• alimohammadiamirhossein / smite
  Pytorch Implementation of "SMITE: Segment Me In TimE" (ICLR 2025)
  ☆211Updated 6 months ago
• orhir / PoseAnything
  A Graph-Based Approach for Category-Agnostic Pose Estimation [ECCV 2024]
  ☆375Updated 10 months ago
• autodistill / autodistill-grounded-sam-2
  Use Segment Anything 2, grounded with Florence-2, to auto-label data for use in training vision models.
  ☆132Updated last year
• Amshaker / MAVOS
  [WACV 2025] Efficient Video Object Segmentation via Modulated Cross-Attention Memory
  ☆58Updated 7 months ago
• Jiahao000 / MosaicFusion
  [IJCV 2024] MosaicFusion: Diffusion Models as Data Augmenters for Large Vocabulary Instance Segmentation
  ☆126Updated last year
• Surrey-UP-Lab / RegionSpot
  Recognize Any Regions
  ☆121Updated 10 months ago
• xushilin1 / RMP-SAM
  [ICLR 2025 oral] RMP-SAM: Towards Real-Time Multi-Purpose Segment Anything
  ☆261Updated 6 months ago
• invictus717 / InteractiveVideo
  InteractiveVideo: User-Centric Controllable Video Generation with Synergistic Multimodal Instructions
  ☆129Updated last year
• czg1225 / SlimSAM
  [NeurIPS 2024] SlimSAM: 0.1% Data Makes Segment Anything Slim
  ☆343Updated 3 weeks ago
• EvolvingLMMs-Lab / RelateAnything
  Relate Anything Model is capable of taking an image as input and utilizing SAM to identify the corresponding mask within the image.
  ☆454Updated 2 years ago