mlsanityData to 7 Oct 2026

RIO: 3D Object Instance Re-Localization in Changing Indoor Environments

arXiv 1908.06109 ↗First posted 16 Aug 2019cs.CVcited by 187

Not on the map. Why?

Cited by 26 in Multimodal LLMs / vision-language models, but placed by its own abstract, which didn’t fit.

Abstract (arXiv)

In this work, we introduce the task of 3D object instance re-localization (RIO): given one or multiple objects in an RGB-D scan, we want to estimate their corresponding 6DoF poses in another 3D scan of the same environment taken at a later point in time. We consider RIO a particularly important task in 3D vision since it enables a wide range of practical applications, including AI-assistants or robots that are asked to find a specific object in a 3D scene. To address this problem, we first introduce 3RScan, a novel dataset and benchmark, which features 1482 RGB-D scans of 478 environments across multiple time steps. Each scene includes several objects whose positions change over time, together with ground truth annotations of object instances and their respective 6DoF mappings among re-scans. Automatically finding 6DoF object poses leads to a particular challenging feature matching task due to varying partial observations and changes in the surrounding context. To this end, we introduce a new data-driven approach that efficiently finds matching features using a fully-convolutional 3D correspondence network operating on multiple spatial scales. Combined with a 6DoF pose optimization, our method outperforms state-of-the-art baselines on our newly-established benchmark, achieving an accuracy of 30.58%.

Key facts. Cited by 187 papers in the map (data through 7 Oct 2026). First posted on arXiv 16 Aug 2019.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 11; 2022: 10; 2023: 23; 2024: 33; 2025: 68; 2026: 42.

187 papers.

Sort:

By area:

  1. 2021Habitat-Matterport 3D Dataset (HM3D): 1000 Large-scale 3D Environments for Embodied AIcited by 579
  2. 2022OpenScene: 3D Scene Understanding with Open Vocabulariescited by 556
  3. 2023An Embodied Generalist Agent in 3D Worldcited by 355
  4. 20233D-VisTA: Pre-trained Transformer for 3D Vision and Text Alignmentcited by 201
  5. 2023LAMM: Language-Assisted Multi-Modal Instruction-Tuning Dataset, Framework, and Benchmarkcited by 169
  6. 2021SceneGraphFusion: Incremental 3D Scene Graph Prediction from RGB-D Sequencescited by 159
  7. 2023EmbodiedScan: A Holistic Multi-Modal 3D Perception Suite Towards Embodied AIcited by 146
  8. 2025RoboBrain: A Unified Brain Model for Robotic Manipulation from Abstract to Concretecited by 134
  9. 2024RoboSpatial: Teaching Spatial Understanding to 2D and 3D Vision-Language Models for Roboticscited by 133
  10. 2024Video-3D LLM: Learning Position-Aware Video Representation for 3D Scene Understandingcited by 131
  11. 2024SceneVerse: Scaling 3D Vision-Language Learning for Grounded Scene Understandingcited by 130
  12. 2024Infinigen Indoors: Photorealistic Indoor Scenes using Procedural Generationcited by 129
38 more
  1. 2024Grounded 3D-LLM with Referent Tokenscited by 111
  2. 2022Habitat-Matterport 3D Semantics Datasetcited by 109
  3. 2025GPT4Scene: Understand 3D Scenes from Videos with Vision-Language Modelscited by 106
  4. 2021Graph-to-3D: End-to-End Generation and Manipulation of 3D Scenes Using Scene Graphscited by 83
  5. 2025MM-Spatial: Exploring 3D Spatial Understanding in Multimodal LLMscited by 72
  6. 2023Visual Programming for Zero-shot Open-Vocabulary 3D Visual Groundingcited by 64
  7. 2025SpatialLM: Training Large Language Models for Structured Indoor Modelingcited by 63
  8. 2023CommonScenes: Generating Commonsense 3D Indoor Scenes with Scene Graph Diffusioncited by 54
  9. 2025Multi-SpatialMLLM: Multi-Frame Spatial Understanding with Multi-Modal Large Language Modelscited by 52
  10. 2025SceneSplat: Gaussian Splatting-based Scene Understanding with Vision-Language Pretrainingcited by 51
  11. 2024Multi-modal Situated Reasoning in 3D Scenescited by 50
  12. 2025Move to Understand a 3D Scene: Bridging Visual Grounding and Exploration for Efficient and Versatile Embodied Navigationcited by 50
  13. 2021Exploiting Edge-Oriented Reasoning for 3D Point-based Scene Graph Analysiscited by 47
  14. 2021MultiBodySync: Multi-Body Segmentation and Motion Estimation via 3D Scan Synchronizationcited by 46
  15. 2023VL-SAT: Visual-Linguistic Semantics Assisted Training for 3D Semantic Scene Graph Prediction in Point Cloudcited by 42
  16. 2024When LLMs step into the 3D World: A Survey and Meta-Analysis of 3D Tasks via Multi-modal Large Language Modelscited by 41
  17. 2024MMScan: A Multi-Modal 3D Scene Dataset with Hierarchical Grounded Language Annotationscited by 40
  18. 2024EmbodiedSAM: Online Segment Any 3D Thing in Real Timecited by 40
  19. 2023Incremental 3D Semantic Scene Graph Prediction from RGB Sequencescited by 39
  20. 2024LSceneLLM: Enhancing Large 3D Scene Understanding Using Adaptive Visual Preferencescited by 36
  21. 2024T2SG: Traffic Topology Scene Graph for Topology Reasoning in Autonomous Drivingcited by 35
  22. 2025MMSI-Video-Bench: A Holistic Benchmark for Video-Based Spatial Intelligencecited by 34
  23. 2021DeepPanoContext: Panoramic 3D Scene Understanding with Holistic Scene Context Graph and Relation-based Optimizationcited by 33
  24. 2022ScanEnts3D: Exploiting Phrase-to-3D-Object Correspondences for Improved Visio-Linguistic Models in 3D Scenescited by 32
  25. 2025Detect Anything 3D in the Wildcited by 32
  26. 2024Search3D: Hierarchical Open-Vocabulary 3D Segmentationcited by 31
  27. 2023SGAligner : 3D Scene Alignment with Scene Graphscited by 30
  28. 2024SceneGraphLoc: Cross-Modal Coarse Visual Localization on 3D Scene Graphscited by 29
  29. 2021ChangeSim: Towards End-to-End Online Scene Change Detection in Industrial Indoor Environmentscited by 28
  30. 2025RoboOS: A Hierarchical Embodied Framework for Cross-Embodiment and Multi-Agent Collaborationcited by 28
  31. 2023SGFormer: Semantic Graph Transformer for Point Cloud-based 3D Scene Graph Generationcited by 27
  32. 20243DGraphLLM: Combining Semantic Graphs and Large Language Models for 3D Scene Understandingcited by 26
  33. 2022Towards Explainable 3D Grounded Visual Question Answering: A New Benchmark and Strong Baselinecited by 25
  34. 20223D VSG: Long-term Semantic Scene Change Prediction through 3D Variable Scene Graphscited by 24
  35. 20223D Segmentation of Humans in Point Clouds with Synthetic Datacited by 24
  36. 2021A Survey on Human-aware Robot Navigationcited by 23
  37. 2025Robix: A Unified Model for Robot Interaction, Reasoning and Planningcited by 23
  38. 2024From Specific-MLLMs to Omni-MLLMs: A Survey on MLLMs Aligned with Multi-modalitiescited by 22

50 most cited of 187 All 187 (JSON)