{"record": {"aliases": ["GridFlow: Structured Latent Flow for Seamless City-Scale 3D Point Cloud Generation"], "artifacts": [{"id": "arxiv:2608.29793", "kind": "paper", "url": "https://arxiv.org/abs/2608.29793"}, {"id": "hf:e32/city3d-multigen", "kind": "dataset", "url": "https://huggingface.co/datasets/e32/City3D-MultiGen"}], "authors": ["Xinyu Wang", "Muhammad Ibrahim", "Atif Mansoor", "Ajmal Mian"], "authors_reference": {"basis": "arxiv_metadata", "retrieved_at": "2026-11-03", "source_key": "claire-radar:2608.29793", "source_url": "https://arxiv.org/abs/2608.29793"}, "categories": ["General AI", "Geometric reasoning", "Vision & 3D", "cs.CV"], "description": {"en": "City3D-MultiGen provides 163K densely annotated tiles with aligned point clouds, satellite images, semantic maps, and elevation data for city-scale 3D point cloud generation evaluation."}, "documents": [{"document_type": "registry_page", "id": "claire_radar:https://arxiv.org/abs/2608.29793", "source": "claire_radar", "source_url": "https://arxiv.org/abs/2608.29793", "title": "City3D-MultiGen"}], "evidence_summary": {"document_count": 1, "model_count": null, "model_count_basis": null}, "key": "claire-radar:2608.29793", "modality": null, "name": "City3D-MultiGen", "openness": {"code_license": null, "data_license": null, "evidence": [], "status": "unknown"}, "provenance": {"confidence": "Medium", "crawl_bundle": "claire_radar_2026-10-14", "crawled_at": "2026-10-14T09:44:51Z", "data_status": "primary-source-indexed", "display_eligible": "true", "origin_record_id": "bm_gridflow-structured-latent-flow-for-seamle_f65faabd", "origin_source": "arxiv", "recognition_confidence": "0.55", "record_sha256": "a72b34b5c4a7cbcca6e9aee17acdcd602b2937b3512dbb206b05a4d8ed8b9ce2", "relation": "introduces", "review_model": "deepseek-v4-pro", "review_state": "ai-reviewed", "reviewed_at": "2026-09-02T05:23:11.715633Z", "source_url": "https://arxiv.org/abs/2608.29793"}, "publisher": null, "released": "2026-08-30", "released_reference": {"basis": "benchmark_release", "source_key": "claire-radar:2608.29793", "source_url": "https://arxiv.org/abs/2608.29793"}, "schema_version": 1, "sizes": [], "slug": "claire-radar-2608-29793", "source": "claire_radar", "source_benchmark_id": "2608.29793", "source_metadata": {"claire_radar": {"adoption30d": null, "aliases": ["GridFlow: Structured Latent Flow for Seamless City-Scale 3D Point Cloud Generation"], "annotation": "Unknown", "applicationDomains": ["General AI"], "area": "Vision & 3D", "attention": {"asOf": "2026-09-02", "attemptedAt": "2026-09-02T05:12:51.621571Z", "githubRepo": null, "githubScope": null, "githubStars": null, "hfDailySubmittedAt": null, "hfDataset": "e32/City3D-MultiGen", "hfDatasetDownloads": 23, "hfDatasetLikes": 0, "hfPaperUpvotes": null, "hfPaperUrl": "https://huggingface.co/papers/2608.29793", "observedAt": "2026-09-02T05:12:51.621571Z", "signalStatus": {"githubStars": {"state": "not_applicable"}, "hfDatasetDownloads": {"observedAt": "2026-09-02T05:12:51.621571Z", "state": "fresh"}, "hfDatasetLikes": {"observedAt": "2026-09-02T05:12:51.621571Z", "state": "fresh"}, "hfPaperUpvotes": {"checkedAt": "2026-09-02T05:12:51.621571Z", "state": "unavailable"}}, "status": "fresh"}, "attentionForecast": {"confidence": "Medium", "horizon": "7d", "reason": "City-scale generation and 3D benchmarks have moderate but specialized interest, and the public dataset supports reproducibility.", "score": 60}, "capabilities": ["Geometric reasoning"], "confidence": "Medium", "construction": "Unknown", "constructionDetail": "Unknown — the indexer does not infer construction details without explicit source evidence.", "copyGeneration": {"generatedAt": "2026-09-02T05:23:11.715633Z", "inputHash": "f03c9b4dfb5254fea7558ad0ce224245d7af25413c7569dcee198b52f40ce0b3", "model": "deepseek-v4-pro"}, "curation": {"canonicalNameEvidence": "pretty_name: City3D-MultiGen", "canonicalNameSource": "official_readme", "decisionReason": "The benchmark is released as a Hugging Face dataset with detailed construction instructions and evaluation metrics.", "model": "deepseek-v4-pro", "reviewedAt": "2026-09-02T05:23:11.715633Z", "state": "ai-reviewed"}, "dataStatus": "primary-source-indexed", "demo": false, "description": "City3D-MultiGen provides 163K densely annotated tiles with aligned point clouds, satellite images, semantic maps, and elevation data for city-scale 3D point cloud generation evaluation.", "displayEligible": true, "domainCuration": {"method": "rules-v1", "state": "auto"}, "evaluationMode": "public_reusable", "evidence": {"reasonCodes": ["benchmark term in abstract", "benchmark release stated in one sentence", "public artifact URL"], "snippet": "To support standardized evaluation, we build on public 3D data sources to introduce \\emph{City3D-MultiGen}, a benchmark of $163$K densely annotated tiles from Melbourne and London with aligned point clouds, satellite images, semantic maps, and elevation data."}, "familyId": "bmf_b304375a5fe0", "firstSeenAt": "2026-09-01", "heat": null, "id": "bm_gridflow-structured-latent-flow-for-seamle_f65faabd", "indexedAt": "2026-09-01T06:28:29.895112Z", "industrySectors": [], "links": {"code": null, "data": "https://huggingface.co/datasets/e32/City3D-MultiGen", "paper": "https://arxiv.org/abs/2608.29793", "pdf": "https://arxiv.org/pdf/2608.29793", "project": null, "report": "https://arxiv.org/abs/2608.29793"}, "metrics": [], "motivation": "Generating realistic 3D city environments from remote sensing data is important for simulation, urban planning, and mixed reality, yet existing point cloud generation methods are limited to single objects or bounded indoor scenes and cannot handle the scale, seamless tiling, and partial observability challenges of city-scale generation.", "name": "City3D-MultiGen", "oneLine": "City3D-MultiGen provides 163K densely annotated tiles with aligned point clouds, satellite images, semantic maps, and elevation data for city-scale 3D point cloud generation evaluation.", "paperTitle": "GridFlow: Structured Latent Flow for Seamless City-Scale 3D Point Cloud Generation", "primaryDomain": "General AI", "publication": {"evidence": null, "evidenceLevel": "unverified", "evidenceUrl": "https://arxiv.org/abs/2608.29793", "source": "arxiv-metadata", "status": "unverified", "venue": null, "verifiedAt": "2026-09-01T06:28:29.895112Z"}, "publications": [], "publishers": [{"name": "e32", "organizationType": "academic-lab", "role": "benchmark-publisher", "sourceUrl": "https://huggingface.co/datasets/e32/City3D-MultiGen"}], "ranking": {"30d": {"confidence": "Low", "coverage": 0.15, "datasetDownloadRank": 34, "datasetRankPopulation": 34, "growth": {"components": {"githubStars": {"normalization": "percentile", "normalized": null, "percentile": null, "value": null}, "hfDatasetDownloads": {"normalization": "percentile", "normalized": null, "percentile": null, "value": null}, "hfPaperUpvotes": {"normalization": "percentile", "normalized": null, "percentile": null, "value": null}}, "confidence": "Low", "coverage": 0.0, "elapsedDays": null, "historyDate": null, "rank": null, "score": null, "windowDays": 30}, "level": {"components": {"githubStars": {"normalization": "log-max", "normalized": null, "value": null}, "hfDatasetDownloads": {"normalization": "log-max", "normalized": 0.3316915830975648, "value": 23}, "hfPaperUpvotes": {"normalization": "log-max", "normalized": null, "value": null}}, "confidence": "Low", "coverage": 0.15, "rank": 41, "score": 47}, "method": "attention-ranking-v13", "rank": 41, "score": 47}, "90d": {"confidence": "Low", "coverage": 0.3, "datasetDownloadRank": 69, "datasetRankPopulation": 70, "growth": {"components": {"githubStars": {"normalization": "percentile", "normalized": null, "percentile": null, "value": null}, "hfDatasetDownloads": {"normalization": "percentile", "normalized": null, "percentile": null, "value": null}, "hfPaperUpvotes": {"normalization": "percentile", "normalized": null, "percentile": null, "value": null}}, "confidence": "Low", "coverage": 0.0, "elapsedDays": null, "historyDate": null, "rank": null, "score": null, "windowDays": 90}, "level": {"components": {"githubStars": {"normalization": "log-max", "normalized": null, "value": null}, "hfDatasetDownloads": {"normalization": "log-max", "normalized": 0.26324659142113743, "value": 23}, "hfPaperUpvotes": {"normalization": "log-max", "normalized": null, "value": null}}, "confidence": "Low", "coverage": 0.3, "rank": 125, "score": 43}, "method": "attention-ranking-v13", "rank": 125, "score": 43}}, "readiness": "Inspectable", "recognitionConfidence": 0.55, "relation": "introduces", "releasedAt": "2026-08-30", "source": {"authors": ["Xinyu Wang", "Muhammad Ibrahim", "Atif Mansoor", "Ajmal Mian"], "categories": ["cs.CV"], "id": "2608.29793", "title": "GridFlow: Structured Latent Flow for Seamless City-Scale 3D Point Cloud Generation", "type": "arxiv", "url": "https://arxiv.org/abs/2608.29793"}, "sourceUpdatedAt": "2026-08-30T13:39:36Z", "topics": ["cs.CV"], "venueAttempts": [], "whyItMatters": "It supports standardized evaluation of city-scale point cloud generation, a task lacking dedicated benchmarks."}}}, "schema_version": 1, "scores_by_source": {}, "siblings": []}
