mlsanityData to 7 Oct 2026

Answerability Fields: Answerable Location Estimation via Diffusion Models

arXiv 2407.18497 ↗First posted 26 Jul 2024cs.CVcited by 1

On the map: Diffusion models → 3D, point cloud and scene generation

Abstract (arXiv)

In an era characterized by advancements in artificial intelligence and robotics, enabling machines to interact with and understand their environment is a critical research endeavor. In this paper, we propose Answerability Fields, a novel approach to predicting answerability within complex indoor environments. Leveraging a 3D question answering dataset, we construct a comprehensive Answerability Fields dataset, encompassing diverse scenes and questions from ScanNet. Using a diffusion model, we successfully infer and evaluate these Answerability Fields, demonstrating the importance of objects and their locations in answering questions within a scene. Our results showcase the efficacy of Answerability Fields in guiding scene-understanding tasks, laying the foundation for their application in enhancing interactions between intelligent agents and their environments.

Key facts. Cited by 1 paper in the map (data through 7 Oct 2026). Placed in 3D, point cloud and scene generation, one of 14 directions in Diffusion models. Builds on 29 of its 36 references that are in the map. First posted on arXiv 26 Jul 2024.

Builds on

29 of 36 references.

References · 29

  1. 2015U-Net: Convolutional Networks for Biomedical Image Segmentationcited by 19,604
  2. 2021High-Resolution Image Synthesis with Latent Diffusion Modelscited by 18,694
  3. 2023Adding Conditional Control to Text-to-Image Diffusion Modelscited by 5,466
  4. 2017ScanNet: Richly-annotated 3D Reconstructions of Indoor Scenescited by 3,088
  5. 2022InstructPix2Pix: Learning to Follow Image Editing Instructionscited by 2,591
  6. 2017Vision-and-Language Navigation: Interpreting visually-grounded navigation instructions in real environmentscited by 1,013
  7. 2022OFA: Unifying Architectures, Tasks, and Modalities Through a Simple Sequence-to-Sequence Learning Frameworkcited by 742
  8. 2018QT-Opt: Scalable Deep Reinforcement Learning for Vision-Based Robotic Manipulationcited by 730
  9. 2019Solving Rubik's Cube with a Robot Handcited by 699
  10. 2019ScanRefer: 3D Object Localization in RGB-D Scans using Natural Languagecited by 446
  11. 2023Generative Multimodal Models are In-Context Learnerscited by 446
  12. 2020Object Goal Navigation using Goal-Oriented Semantic Explorationcited by 421
17 more
  1. 2022Visual Language Maps for Robot Navigationcited by 362
  2. 2022DiffusionDet: Diffusion Model for Object Detectioncited by 354
  3. 2020Transporter Networks: Rearranging the Visual World for Robotic Manipulationcited by 342
  4. 2021ScanQA: 3D Question Answering for Spatial Scene Understandingcited by 340
  5. 2017Embodied Question Answeringcited by 335
  6. 2022SQA3D: Situated Question Answering in 3D Scenescited by 303
  7. 2023ConceptFusion: Open-set Multimodal 3D Mappingcited by 302
  8. 2020ObjectNav Revisited: On Evaluation of Embodied Agents Navigating to Objectscited by 240
  9. 2023Any-to-Any Generation via Composable Diffusioncited by 203
  10. 2022CLIP-Fields: Weakly Supervised Semantic Fields for Robotic Memorycited by 164
  11. 2022PONI: Potential Functions for ObjectGoal Navigation with Interaction-free Learningcited by 149
  12. 2019Embodied Question Answering in Photorealistic Environments with Point Cloud Perceptioncited by 103
  13. 2018Neural Modular Control for Embodied Question Answeringcited by 56
  14. 2022Look Outside the Room: Synthesizing A Consistent Long-Term 3D Scene Video from A Single Imagecited by 55
  15. 2022DiffusionInst: Diffusion Model for Instance Segmentationcited by 49
  16. 2023World Models via Policy-Guided Trajectory Diffusioncited by 34
  17. 2023DiPPeR: Diffusion-based 2D Path Planner applied on Legged Robotscited by 20

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2026: 1.

1 paper.

  1. 2026E3VS-Bench: A Benchmark for Viewpoint-Dependent Active Perception in 3D Gaussian Splatting Scenescited by 3

Similar, not cited

Close in wording, no citation either way

  1. 2025Embodied Intelligence for 3D Understanding: A Survey on 3D Scene Question Answering
  2. 20253D-MoRe: Unified Modal-Contextual Reasoning for Embodied Question Answering
  3. 2024Space3D-Bench: Spatial 3D Question Answering Benchmark
  4. 2024Multi-modal Situated Reasoning in 3D Scenes
  5. 2026Hierarchical Floorplan-Guided Vision-Language Exploration for Embodied Question Answering ↗
  6. 2025CityEQA: A Hierarchical LLM Agent on Embodied Question Answering Benchmark in City Space
  7. 2026IDEAL-Bench: Indoor Dataset and Evaluation suite for Analyzing 3D Layout reasoning
  8. 2024GraphEQA: Using 3D Semantic Scene Graphs for Real-time Embodied Question Answering