Alternatives and similar repositories for 3D-LLM

Users that are interested in 3D-LLM are comparing it to the libraries listed below

• ActiveVisionLab / Awesome-LLM-3D

  View on GitHub
  Awesome-LLM-3D: a curated list of Multi-modal Large Language Model in 3D world Resources
  ☆2,115Feb 3, 2026Updated last week
• Open3DA / LL3DA

  View on GitHub
  [CVPR 2024] "LL3DA: Visual Interactive Instruction Tuning for Omni-3D Understanding, Reasoning, and Planning"; an interactive Large Langu…
  ☆311Jul 17, 2024Updated last year
• InternRobotics / PointLLM

  View on GitHub
  [ECCV 2024 Best Paper Candidate & TPAMI 2025] PointLLM: Empowering Large Language Models to Understand Point Clouds
  ☆973Aug 14, 2025Updated 6 months ago
• baaivision / Uni3D

  View on GitHub
  [ICLR'24 Spotlight] Uni3D: 3D Visual Representation from BAAI
  ☆642Jan 12, 2026Updated last month
• UMass-Embodied-AGI / 3D-VLA

  View on GitHub
  [ICML 2024] 3D-VLA: A 3D Vision-Language-Action Generative World Model
  ☆620Oct 29, 2024Updated last year
• ZCMax / LLaVA-3D

  View on GitHub
  [ICCV 2025] A Simple yet Effective Pathway to Empowering LLaVA to Understand and Interact with 3D World
  ☆372Oct 21, 2025Updated 3 months ago
• ZiyuGuo99 / Point-Bind_Point-LLM

  View on GitHub
  Align 3D Point Cloud with Multi-modalities for Large Language Models
  ☆459Dec 9, 2023Updated 2 years ago
• InternRobotics / EmbodiedScan

  View on GitHub
  [CVPR 2024 & NeurIPS 2024] EmbodiedScan: A Holistic Multi-Modal 3D Perception Suite Towards Embodied AI
  ☆651Jun 13, 2025Updated 8 months ago
• embodied-generalist / embodied-generalist

  View on GitHub
  [ICML 2024] LEO: An Embodied Generalist Agent in 3D World
  ☆475Apr 20, 2025Updated 9 months ago
• ZzZZCHS / Chat-Scene

  View on GitHub
  Code for "Chat-Scene: Bridging 3D Scene and Large Language Models with Object Identifiers" (NeurIPS 2024)
  ☆206Oct 20, 2025Updated 3 months ago
• scene-verse / SceneVerse

  View on GitHub
  Official implementation of ECCV24 paper "SceneVerse: Scaling 3D Vision-Language Learning for Grounded Scene Understanding"
  ☆278Mar 19, 2025Updated 10 months ago
• 3d-vista / 3D-VisTA

  View on GitHub
  Official implementation of ICCV 2023 paper "3D-VisTA: Pre-trained Transformer for 3D Vision and Text Alignment"
  ☆217Sep 7, 2023Updated 2 years ago
• pengsongyou / openscene

  View on GitHub
  [CVPR'23] OpenScene: 3D Scene Understanding with Open Vocabularies
  ☆801Oct 27, 2023Updated 2 years ago
• ATR-DBI / ScanQA

  View on GitHub
  ☆150Aug 23, 2023Updated 2 years ago
• Pointcept / SegmentAnything3D

  View on GitHub
  [ICCV'23 Workshop] SAM3D: Segment Anything in 3D Scenes
  ☆1,304Apr 21, 2024Updated last year
• UMass-Embodied-AGI / MultiPLY

  View on GitHub
  Code for MultiPLY: A Multisensory Object-Centric Embodied Large Language Model in 3D World
  ☆133Oct 24, 2024Updated last year
• qizekun / ShapeLLM

  View on GitHub
  [ECCV 2024] ShapeLLM: Universal 3D Object Understanding for Embodied Interaction
  ☆225Oct 8, 2024Updated last year
• CVMI-Lab / PLA

  View on GitHub
  (CVPR 2023) PLA: Language-Driven Open-Vocabulary 3D Scene Understanding & (CVPR2024) RegionPLC: Regional Point-Language Contrastive Learn…
  ☆298Jun 28, 2024Updated last year
• evelinehong / 3D-CLR-Official

  View on GitHub
  [CVPR 2023] Code for "3D Concept Learning and Reasoning from Multi-View Images"
  ☆84Jan 20, 2024Updated 2 years ago
• sled-group / chat-with-nerf

  View on GitHub
  [ICRA 2024] Chat with NeRF enables users to interact with a NeRF model by typing in natural language.
  ☆320Oct 10, 2025Updated 4 months ago
• OpenGVLab / PonderV2

  View on GitHub
  [T-PAMI 2025] PonderV2: Pave the Way for 3D Foundation Model with A Universal Pre-training Paradigm
  ☆370Sep 30, 2025Updated 4 months ago
• concept-fusion / concept-fusion

  View on GitHub
  Code release for ConceptFusion [RSS 2023]
  ☆228Sep 23, 2023Updated 2 years ago
• InternRobotics / Grounded_3D-LLM

  View on GitHub
  Code&Data for Grounded 3D-LLM with Referent Tokens
  ☆132Jan 5, 2025Updated last year
• Chat-3D / Chat-3D

  View on GitHub
  Code for "Chat-3D: Data-efficiently Tuning Large Language Model for Universal Dialogue of 3D Scenes"
  ☆56Mar 28, 2024Updated last year
• mbanani / probe3d

  View on GitHub
  [CVPR 2024] Probing the 3D Awareness of Visual Foundation Models
  ☆348Dec 1, 2025Updated 2 months ago
• vision-x-nyu / thinking-in-space

  View on GitHub
  Official repo and evaluation implementation of VSI-Bench
  ☆670Aug 5, 2025Updated 6 months ago
• minghanqin / LangSplat

  View on GitHub
  Official implementation of the paper "LangSplat: 3D Language Gaussian Splatting" [CVPR2024 Highlight]
  ☆995Oct 10, 2025Updated 4 months ago
• omniobject3d / OmniObject3D

  View on GitHub
  [ CVPR 2023 Award Candidate ] OmniObject3D: Large-Vocabulary 3D Object Dataset for Realistic Perception, Reconstruction and Generation
  ☆516Sep 2, 2024Updated last year
• staymylove / 3DMIT

  View on GitHub
  Code of 3DMIT: 3D MULTI-MODAL INSTRUCTION TUNING FOR SCENE UNDERSTANDING
  ☆31Jul 26, 2024Updated last year
• kerrj / lerf

  View on GitHub
  Code for LERF: Language Embedded Radiance Fields
  ☆720Jul 9, 2024Updated last year
• JonasSchult / Mask3D

  View on GitHub
  Mask3D predicts accurate 3D semantic instances achieving state-of-the-art on ScanNet, ScanNet200, S3DIS and STPLS3D.
  ☆709Oct 29, 2023Updated 2 years ago
• youquanl / Segment-Any-Point-Cloud

  View on GitHub
  [NeurIPS'23 Spotlight] Segment Any Point Cloud Sequences by Distilling Vision Foundation Models
  ☆643Dec 16, 2023Updated 2 years ago
• salesforce / ULIP

  View on GitHub
  ☆582Jan 21, 2026Updated 3 weeks ago
• 3dlg-hcvc / multi3drefer

  View on GitHub
  [ICCV 2023] Multi3DRefer: Grounding Text Description to Multiple 3D Objects
  ☆94Oct 18, 2025Updated 3 months ago
• Pointcept / GPT4Point

  View on GitHub
  [CVPR'24 Highlight] GPT4Point: A Unified Framework for Point-Language Understanding and Generation.
  ☆438Apr 27, 2024Updated last year
• Anything-of-anything / Anything-3D

  View on GitHub
  Segment-Anything + 3D. Let's lift anything to 3D.
  ☆1,606Jun 12, 2023Updated 2 years ago
• naver / dust3r

  View on GitHub
  DUSt3R: Geometric 3D Vision Made Easy
  ☆6,950Sep 24, 2025Updated 4 months ago
• CUT3R / CUT3R

  View on GitHub
  Official implementation of Continuous 3D Perception Model with Persistent State
  ☆1,329Aug 27, 2025Updated 5 months ago
• Lakonik / SSDNeRF

  View on GitHub
  [ICCV 2023] Single-Stage Diffusion NeRF
  ☆447Apr 20, 2024Updated last year