{"record": {"aliases": [], "artifacts": [{"id": "arxiv:2607.03110", "kind": "paper", "url": "https://arxiv.org/abs/2607.03110"}, {"id": "gh:leo-liuyao/expomotion", "kind": "repo", "url": "https://github.com/Leo-LiuYao/ExpoMotion"}], "authors": ["Yao Liu", "Lishen Qu", "Shihao Zhou", "Jie Liang", "Hui Zeng", "Yabin Peng", "Huipeng Lin", "Lei Zhang", "Jufeng Yang"], "authors_reference": {"basis": "arxiv_metadata", "retrieved_at": "2026-11-03", "source_key": "claire-radar:2607.03110", "source_url": "https://arxiv.org/abs/2607.03110"}, "categories": ["General AI", "Vision & 3D", "cs.CV"], "description": {"en": "ExpoMotion is a large-scale benchmark for multi-exposure fusion with dynamic scenes, containing 1,738 sequences and 10,909 images across diverse environments. It provides high-fidelity ground truth for reference-based evaluation and a separate set for no-reference evaluation. The benchmark includes training and testing splits with controlled and real-world motions."}, "documents": [{"document_type": "registry_page", "id": "claire_radar:https://arxiv.org/abs/2607.03110", "source": "claire_radar", "source_url": "https://arxiv.org/abs/2607.03110", "title": "ExpoMotion"}], "evidence_summary": {"document_count": 1, "model_count": null, "model_count_basis": null}, "key": "claire-radar:2607.03110", "modality": null, "name": "ExpoMotion", "openness": {"code_license": null, "data_license": null, "evidence": [], "status": "unknown"}, "provenance": {"confidence": "High", "crawl_bundle": "claire_radar_2026-10-14", "crawled_at": "2026-10-14T09:44:51Z", "data_status": "primary-source-indexed", "display_eligible": "unknown", "origin_record_id": "bm_expomotion_345f5881", "origin_source": "arxiv", "recognition_confidence": "1.0", "record_sha256": "7d7a5e26593667fb2b8702e3e93a9889f0cbfc4bf2f2dcc7400882503245120a", "relation": "introduces", "review_state": "unreviewed", "source_url": "https://arxiv.org/abs/2607.03110"}, "publisher": null, "released": "2026-07-03", "released_reference": {"basis": "benchmark_release", "source_key": "claire-radar:2607.03110", "source_url": "https://arxiv.org/abs/2607.03110"}, "schema_version": 1, "sizes": [], "slug": "claire-radar-2607-03110", "source": "claire_radar", "source_benchmark_id": "2607.03110", "source_metadata": {"claire_radar": {"adoption30d": null, "aliases": [], "annotation": "Unknown", "applicationDomains": ["General AI"], "area": "Vision & 3D", "attention": {"asOf": "2026-10-05", "attemptedAt": "2026-10-04T15:31:48.030916Z", "githubRepo": "https://github.com/Leo-LiuYao/ExpoMotion", "githubScope": "benchmark_repo", "githubStars": 5, "hfDailySubmittedAt": null, "hfDataset": null, "hfDatasetDownloads": null, "hfDatasetLikes": null, "hfPaperUpvotes": null, "hfPaperUrl": "https://huggingface.co/papers/2607.03110", "observedAt": "2026-10-04T15:31:48.030916Z", "signalStatus": {"githubStars": {"observedAt": "2026-10-04T15:31:48.030916Z", "state": "fresh"}, "hfDatasetDownloads": {"state": "not_applicable"}, "hfDatasetLikes": {"state": "not_applicable"}, "hfPaperUpvotes": {"checkedAt": "2026-10-04T15:31:48.030916Z", "state": "unavailable"}}, "status": "fresh"}, "capabilities": [], "confidence": "High", "construction": "Transform Existing", "constructionDetail": "Unknown — the indexer does not infer construction details without explicit source evidence.", "copyGeneration": {"generatedAt": "2026-08-20T15:22:10.044731Z", "inputHash": "13d77869c5a256919370d81a4ccbc50f4705a49fc28cd32745042ea863e6c26e", "model": "deepseek-v4-flash"}, "dataStatus": "primary-source-indexed", "demo": false, "description": "ExpoMotion is a large-scale benchmark for multi-exposure fusion with dynamic scenes, containing 1,738 sequences and 10,909 images across diverse environments. It provides high-fidelity ground truth for reference-based evaluation and a separate set for no-reference evaluation. The benchmark includes training and testing splits with controlled and real-world motions.", "domainCuration": {"method": "rules-v1", "state": "auto"}, "evidence": {"reasonCodes": ["exact coined title identity tied to benchmark evidence", "benchmark release stated in one sentence", "public artifact URL"], "snippet": "In response, we introduce ExpoMotion, a large-scale benchmark designed to evaluate deghosting capabilities."}, "familyId": "bmf_3b0426612bd6", "firstSeenAt": "2026-08-19", "githubIndex": {"candidateCount": 0, "indexedAt": "2026-09-17T04:40:34.111665+00:00", "repositories": [{"evidence": [{"basis": "existing-code-link", "linkedUrl": "https://github.com/Leo-LiuYao/ExpoMotion", "url": "https://github.com/Leo-LiuYao/ExpoMotion"}, {"basis": "existing-metric-association", "linkedUrl": "https://github.com/Leo-LiuYao/ExpoMotion", "url": "https://huggingface.co/papers/2607.03110"}, {"basis": "linked-from-report", "linkedUrl": "https://github.com/Leo-LiuYao/ExpoMotion", "url": "https://arxiv.org/abs/2607.03110"}, {"basis": "linked-from-report", "linkedUrl": "https://github.com/Leo-LiuYao/ExpoMotion.", "url": "https://arxiv.org/abs/2607.03110"}], "scope": "benchmark_repo", "url": "https://github.com/Leo-LiuYao/ExpoMotion", "verification": "source-linked"}], "status": "linked"}, "heat": null, "id": "bm_expomotion_345f5881", "indexedAt": "2026-08-19T11:05:13.395391Z", "industrySectors": [], "links": {"code": "https://github.com/Leo-LiuYao/ExpoMotion", "data": null, "hfPaper": "https://huggingface.co/papers/2607.03110", "paper": "https://arxiv.org/abs/2607.03110", "pdf": "https://arxiv.org/pdf/2607.03110", "project": null, "report": "https://arxiv.org/abs/2607.03110"}, "metrics": [], "motivation": "Multi-Exposure Fusion (MEF) effectively extends dynamic range, but practical deployment is hindered by motion-induced ghosting and the scarcity of high-quality dynamic benchmarks.", "name": "ExpoMotion", "oneLine": "ExpoMotion is a large-scale benchmark for multi-exposure fusion with dynamic scenes, containing 1,738 sequences and 10,909 images across diverse environments. It provides high-fidelity ground truth for reference-based evaluation and a separate set for no-reference evaluation. The benchmark includes training and testing splits with controlled and real-world motions.", "paperTitle": "ExpoMotion: A Large-Scale Benchmark and A Householder Projection Network for Multi-Exposure Fusion", "primaryDomain": "General AI", "publication": {"evidence": "Accepted by ECCV 2026", "evidenceLevel": "author-claim", "evidenceUrl": "https://arxiv.org/abs/2607.03110", "source": "arxiv-comments", "status": "acceptance_claimed", "venue": "ECCV 2026", "verifiedAt": "2026-10-14T01:46:58.058199Z"}, "publications": [], "publishers": [{"name": "ExpoMotion Project", "organizationType": "academic-lab", "role": "benchmark-publisher", "sourceUrl": "https://github.com/Leo-LiuYao/ExpoMotion"}], "ranking": {}, "readiness": "Runnable", "recognitionConfidence": 1.0, "relation": "introduces", "releasedAt": "2026-07-03", "source": {"authors": ["Yao Liu", "Lishen Qu", "Shihao Zhou", "Jie Liang", "Hui Zeng", "Yabin Peng", "Huipeng Lin", "Lei Zhang", "Jufeng Yang"], "categories": ["cs.CV"], "id": "2607.03110", "title": "ExpoMotion: A Large-Scale Benchmark and A Householder Projection Network for Multi-Exposure Fusion", "type": "arxiv", "url": "https://arxiv.org/abs/2607.03110"}, "sourceUpdatedAt": "2026-07-03T08:46:10Z", "topics": ["cs.CV"], "venueAttempts": [{"decisionRaw": "Accepted by ECCV 2026", "evidence": [{"level": "author-claim", "observedAt": "2026-10-14T01:46:58.058199Z", "rawValue": "Accepted by ECCV 2026", "sourceType": "arxiv-comments", "sourceUrl": "https://arxiv.org/abs/2607.03110"}], "reviewStatus": "accepted", "venueName": "ECCV 2026"}], "whyItMatters": "Existing multi-exposure fusion benchmarks often neglect dynamic scenes and lack reliable ground truth, hindering evaluation of deghosting capabilities. ExpoMotion addresses this gap by providing a large-scale dataset with high-quality ground truth, enabling reproducible comparison of methods that handle motion-induced artifacts. This supports practical deployment in real-world scenarios where motion is common."}}}, "schema_version": 1, "scores_by_source": {}, "siblings": []}
