mlsanityData to 7 Oct 2026

IGLOSS: Image Generation for Lidar Open-vocabulary Semantic Segmentation

arXiv 2604.01361 ↗First posted 1 Apr 2026cs.CVcited by 0

Not on the map. Why?

Abstract (arXiv)

This paper presents a new method for the zero-shot open-vocabulary semantic segmentation (OVSS) of 3D automotive lidar data. To circumvent the recognized image-text modality gap that is intrinsic to approaches based on Vision Language Models (VLMs) such as CLIP, our method relies instead on image generation from text, to create prototype images. Given a 3D network distilled from a 2D Vision Foundation Model (VFM), we then label a point cloud by matching 3D point features with 2D image features of these prototypes. Our method is state-of-the-art for OVSS on nuScenes and SemanticKITTI. Code, pre-trained models, and generated images are available at https://github.com/valeoai/IGLOSS.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 103 of its 119 references that are in the map. First posted on arXiv 1 Apr 2026.

Builds on

103 of 119 references.

References · 103

  1. 2021Learning Transferable Visual Models From Natural Language Supervisioncited by 33,456
  2. 2021High-Resolution Image Synthesis with Latent Diffusion Modelscited by 18,694
  3. 2023Segment Anythingcited by 8,158
  4. 2023Visual Instruction Tuningcited by 7,792
  5. 2023DINOv2: Learning Robust Visual Features without Supervisioncited by 7,764
  6. 2021Emerging Properties in Self-Supervised Vision Transformerscited by 6,893
  7. 2019nuScenes: A multimodal dataset for autonomous drivingcited by 4,485
  8. 2022LAION-5B: An open large-scale dataset for training next generation image-text modelscited by 4,131
  9. 2021Scaling Up Visual and Vision-Language Representation Learning With Noisy Text Supervisioncited by 3,848
  10. 2025Gemini 2.5: Pushing the Frontier with Advanced Reasoning, Multimodality, Long Context, and Next Generation Agentic Capabilitiescited by 3,655
  11. 2016Gaussian Error Linear Units (GELUs)cited by 3,431
  12. 2023Grounding DINO: Marrying DINO with Grounded Pre-Training for Open-Set Object Detectioncited by 3,274
38 more
  1. 2023Sigmoid Loss for Language Image Pre-Trainingcited by 3,048
  2. 2024SAM 2: Segment Anything in Images and Videoscited by 2,784
  3. 2021Learning to Prompt for Vision-Language Modelscited by 2,269
  4. 2022Visual Prompt Tuningcited by 1,674
  5. 2022Conditional Prompt Learning for Vision-Language Modelscited by 1,427
  6. 2020Understanding Contrastive Representation Learning through Alignment and Uniformity on the Hyperspherecited by 1,393
  7. 2025SigLIP 2: Multilingual Vision-Language Encoders with Improved Semantic Understanding, Localization, and Dense Featurescited by 1,127
  8. 2016Deep Networks with Stochastic Depthcited by 973
  9. 2024Grounded SAM: Assembling Open-World Models for Diverse Visual Taskscited by 914
  10. 2021Open-vocabulary Object Detection via Vision and Language Knowledge Distillationcited by 903
  11. 2025SAM 3: Segment Anything with Conceptscited by 835
  12. 2022Language-driven Semantic Segmentationcited by 711
  13. 2022MaPLe: Multi-modal Prompt Learningcited by 685
  14. 2021Extract Free Dense Labels from CLIPcited by 580
  15. 2022OpenScene: 3D Scene Understanding with Open Vocabulariescited by 556
  16. 2022Mind the Gap: Understanding the Modality Gap in Multi-modal Contrastive Representation Learningcited by 553
  17. 2023Segment Everything Everywhere All at Oncecited by 546
  18. 2021Large Scale Interactive Motion Forecasting for Autonomous Driving : The Waymo Open Motion Datasetcited by 532
  19. 2021Scaling Open-Vocabulary Image Segmentation with Image-Level Labelscited by 471
  20. 2020Rethinking Few-Shot Image Classification: a Good Embedding Is All You Need?cited by 435
  21. 2021Supervision Exists Everywhere: A Data Efficient Contrastive Language-Image Pre-training Paradigmcited by 405
  22. 2023InstaFlow: One Step is Enough for High-Quality Diffusion-Based Text-to-Image Generationcited by 387
  23. 2022Test-Time Prompt Tuning for Zero-Shot Generalization in Vision-Language Modelscited by 379
  24. 2023EVA-02: A Visual Representation for Neon Genesiscited by 377
  25. 2022Tip-Adapter: Training-free Adaption of CLIP for Few-shot Classificationcited by 355
  26. 2022Visual Classification via Description from Large Language Modelscited by 331
  27. 2023Your Diffusion Model is Secretly a Zero-Shot Classifiercited by 301
  28. 2023Side Adapter Network for Open-Vocabulary Semantic Segmentationcited by 296
  29. 2022What does a platypus look like? Generating customized prompts for zero-shot image classificationcited by 263
  30. 2023A Simple Framework for Open-Vocabulary Segmentation and Detectioncited by 197
  31. 2022MaskCLIP: Masked Self-Distillation Advances Contrastive Language-Image Pretrainingcited by 187
  32. 2021PandaSet: Advanced Sensor Suite Dataset for Autonomous Drivingcited by 186
  33. 2023Cut and Learn for Unsupervised Object Detection and Instance Segmentationcited by 186
  34. 2023CLIP2Scene: Towards Label-efficient 3D Scene Understanding by CLIPcited by 178
  35. 2023Diverse Data Augmentation with Diffusions for Effective Test-time Prompt Tuningcited by 150
  36. 2023Text-to-Image Diffusion Models are Zero-Shot Classifierscited by 140
  37. 2024Efficient Test-Time Adaptation of Vision-Language Modelscited by 138
  38. 2022Open-Vocabulary Universal Image Segmentation with MaskCLIPcited by 131

50 most cited of 103 All 103 (JSON)

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2026Lang3DSeg: Annotation-Free Open-Vocabulary 3D Segmentation with Point Transformers
  2. 2026SENSE: Stereo OpEN Vocabulary SEmantic Segmentation
  3. 2024Find n' Propagate: Open-Vocabulary 3D Object Detection in Urban Environments
  4. 2024Global-Local Collaborative Inference with LLM for Lidar-Based Open-Vocabulary Detection
  5. 2026Open-Vocabulary Domain Generalization in Urban-Scene Segmentation
  6. 2026Bridging the Modality Gap in Roadside LiDAR: A Training-Free Vision-Language Model Framework for Vehicle Classification
  7. 2023Neural Implicit Vision-Language Feature Fields
  8. 2026Open-vocabulary 3D scene perception in industrial environments