{"paper":{"title":"OmniLiDAR: A Unified Diffusion Framework for Multi-Domain 3D LiDAR Generation","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"A single text-conditioned diffusion model generates realistic LiDAR scans across eight domains spanning weather, sensors, and platforms.","cross_cats":["cs.RO"],"primary_cat":"cs.CV","authors_text":"Ao Liang, Ben Fei, Dekai Zhu, Lingdong Kong, Runnan Chen, Tongliang Liu, Wanli Ouyang, Weidong Yang, Xiang Xu, Xin Li, Yang Wu, Youquan Liu","submitted_at":"2026-05-13T17:42:20Z","abstract_excerpt":"LiDAR scene generation is increasingly important for scalable simulation and synthetic data creation, especially under diverse sensing conditions that are costly to capture at scale. Typically, diffusion-based LiDAR generators are developed under single-domain settings, requiring separate models for different datasets or sensing conditions and hindering unified, controllable synthesis under heterogeneous distribution shifts. To this end, we present OmniLiDAR, a unified text-conditioned diffusion framework that generates LiDAR scans in a shared range-image representation across eight representa"},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"OmniLiDAR generates LiDAR scans in a shared range-image representation across eight representative domains with strong generation fidelity and consistent gains in downstream use cases including generative data augmentation for LiDAR semantic segmentation and 3D object detection.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"That mixing domains within each mini-batch combined with text conditioning and the proposed CDFM and DAFS modules enables effective unified training without needing domain-isolated optimization or suffering from negative transfer across heterogeneous shifts.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"A unified text-conditioned diffusion model generates high-fidelity LiDAR scans across eight domains spanning weather, sensor, and platform shifts using cross-domain training and feature modeling.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"A single text-conditioned diffusion model generates realistic LiDAR scans across eight domains spanning weather, sensors, and platforms.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"8b8f1f4e101ccc7835f2dd2d59cee2e92f0fa211e800acac6ed7c5d51af6c859"},"source":{"id":"2605.13815","kind":"arxiv","version":1},"verdict":{"id":"2e7e691b-61ed-46ff-99ff-496ffe6d9be6","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-14T19:16:58.362102Z","strongest_claim":"OmniLiDAR generates LiDAR scans in a shared range-image representation across eight representative domains with strong generation fidelity and consistent gains in downstream use cases including generative data augmentation for LiDAR semantic segmentation and 3D object detection.","one_line_summary":"A unified text-conditioned diffusion model generates high-fidelity LiDAR scans across eight domains spanning weather, sensor, and platform shifts using cross-domain training and feature modeling.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"That mixing domains within each mini-batch combined with text conditioning and the proposed CDFM and DAFS modules enables effective unified training without needing domain-isolated optimization or suffering from negative transfer across heterogeneous shifts.","pith_extraction_headline":"A single text-conditioned diffusion model generates realistic LiDAR scans across eight domains spanning weather, sensors, and platforms."},"references":{"count":106,"sample":[{"doi":"","year":2023,"title":"UniSeg: A unified multi-modal LiDAR segmentation network and the OpenPCSeg codebase,","work_id":"abb3c108-20a3-4e54-b693-a86024691290","ref_index":1,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2021,"title":"Deep learning for LiDAR point clouds in autonomous driving: A review,","work_id":"89a9a192-b5ec-43af-b870-c1625c0f8e2a","ref_index":2,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2023,"title":"LoGoNet: Towards accurate 3D object detection with local-to-global cross-modal fusion,","work_id":"a4f7328c-0474-401b-b2f2-24629cdec7a8","ref_index":3,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2026,"title":"Xiaomi OneVL: One-Step Latent Reasoning and Planning with Vision-Language Explanation","work_id":"50a8fe28-0142-433c-8da4-bd231fd02f23","ref_index":4,"cited_arxiv_id":"2604.18486","is_internal_anchor":true},{"doi":"","year":2025,"title":"Worldlens: Full-spectrum evaluations of driving world models in real world","work_id":"52b9a2ed-a099-4858-8787-4578c04dc509","ref_index":5,"cited_arxiv_id":"","is_internal_anchor":false}],"resolved_work":106,"snapshot_sha256":"c3d83780bd8c438cc9b1611d50b52d7b7448c4359ea6f458343d078c3d61e7a4","internal_anchors":3},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"}