mlsanityData to 7 Oct 2026

SweeperBot: Making 3D Browsing Accessible through View Analysis and Visual Question Answering

arXiv 2511.14567 ↗First posted 18 Nov 2025cs.HC cs.AIcited by 0

Not on the map. Why?

Abstract (arXiv)

Accessing 3D models remains challenging for Screen Reader (SR) users. While some existing 3D viewers allow creators to provide alternative text, they often lack sufficient detail about the 3D models. Grounded on a formative study, this paper introduces SweeperBot, a system that enables SR users to leverage visual question answering to explore and compare 3D models. SweeperBot answers SR users' visual questions by combining an optimal view selection technique with the strength of generative- and recognition-based foundation models. An expert review with 10 Blind and Low-Vision (BLV) users with SR experience demonstrated the feasibility of using SweeperBot to assist BLV users in exploring and comparing 3D models. The quality of the descriptions generated by SweeperBot was validated by a second survey study with 30 sighted participants.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 33 of its 97 references that are in the map. First posted on arXiv 18 Nov 2025.

Builds on

33 of 97 references.

References · 33

  1. 2021Learning Transferable Visual Models From Natural Language Supervisioncited by 33,456
  2. 2019Sentence-BERT: Sentence Embeddings using Siamese BERT-Networkscited by 9,049
  3. 2023BLIP-2: Bootstrapping Language-Image Pre-training with Frozen Image Encoders and Large Language Modelscited by 6,069
  4. 2019BERTScore: Evaluating Text Generation with BERTcited by 5,462
  5. 2022BLIP: Bootstrapping Language-Image Pre-training for Unified Vision-Language Understanding and Generationcited by 4,310
  6. 2016SQuAD: 100,000+ Questions for Machine Comprehension of Textcited by 4,115
  7. 2023Grounding DINO: Marrying DINO with Grounded Pre-Training for Open-Set Object Detectioncited by 3,274
  8. 2017ScanNet: Richly-annotated 3D Reconstructions of Indoor Scenescited by 3,088
  9. 2016Making the V in VQA Matter: Elevating the Role of Image Understanding in Visual Question Answeringcited by 2,498
  10. 2015VQA: Visual Question Answeringcited by 2,489
  11. 2018VizWiz Grand Challenge: Answering Visual Questions from Blind Peoplecited by 852
  12. 2023ViperGPT: Visual Inference via Python Execution for Reasoningcited by 591
21 more
  1. 2021ScanQA: 3D Question Answering for Spatial Scene Understandingcited by 340
  2. 2023Scalable 3D Captioning with Pretrained Modelscited by 201
  3. 2023LAMM: Language-Assisted Multi-Modal Instruction-Tuning Dataset, Framework, and Benchmarkcited by 169
  4. 2023SAM3D: Segment Anything in 3D Scenescited by 155
  5. 2024ShapeLLM: Universal 3D Object Understanding for Embodied Interactioncited by 133
  6. 2024Multi-modal Situated Reasoning in 3D Scenescited by 50
  7. 20213D Question Answeringcited by 41
  8. 2023Improving Automatic VQA Evaluation Using Large Language Modelscited by 37
  9. 2024View Selection for 3D Captioning via Diffusion Rankingcited by 31
  10. 2024Visual Fact Checker: Enabling High-Fidelity Detailed Caption Generationcited by 28
  11. 2023A Comprehensive Evaluation of GPT-4V on Knowledge-Intensive Visual Question Answeringcited by 23
  12. 2024Bridging the Gap between 2D and 3D Visual Question Answering: A Fusion Approach for 3D VQAcited by 21
  13. 20243D Vision and Language Pretraining with Large-Scale Synthetic Datacited by 21
  14. 2023GenAssist: Making Image Generation Accessiblecited by 18
  15. 2023VizAbility: Enhancing Chart Accessibility with LLM-based Conversational Interactioncited by 12
  16. 2024Evaluating Zero-Shot GPT-4V Performance on 3D Visual Question Answering Benchmarkscited by 10
  17. 2024MemoVis: A GenAI-Powered Tool for Creating Companion Reference Images for 3D Design Feedbackcited by 7
  18. 2023ImageAssist: Tools for Enhancing Touchscreen-Based Image Exploration Systems for Blind and Low Vision Userscited by 6
  19. 2021Revamp: Enhancing Accessible Information Seeking Experience of Online Shopping for Blind or Low Vision Userscited by 4
  20. 2023PaperToPlace: Transforming Instruction Documents into Spatialized and Context-Aware Mixed Reality Experiencescited by 2
  21. 2025VRSight: An AI-Driven Scene Description System to Improve Virtual Reality Accessibility for Blind Peoplecited by 2

Built on by

Not cited yet.