AI 服務暫時不可用，以下為來源正文，待恢復後補全翻譯。
[Submitted on 20 Oct 2026] Title:HorizonComposer: Spatiotemporally Consistent Driving Video Editing with Enriched Traffic Semantics View a PDF of the paper titled HorizonComposer: Spatiotemporally Consistent Driving Video Editing with Enriched Traffic Semantics, by Mauricio Soroco and 7 other authors View PDF HTML (experimental) Abstract:Instruction-guided video generative models offer a scalable solution for stress-testing autonomous driving systems by simulating diverse environmental conditions. However, driving scenes operate within a dense Operational Design Domain (ODD) governed by strict traffic semantics. When applied to global driving-condition edits, general-purpose instruction-guided video editors frequently corrupt these semantics, leading to structural hallucinations and ``temporal shock.'' This work distills and protects traffic semantics during video editing at three levels. First, we construct a hybrid dataset by combining temporally aligned real-world videos with synthetic edits, balancing foundational scene structure with unambiguous appearance signals. Second, during training, we adapt advantage conditioning from offline reinforcement learning to align the model using dense rewards. We extract dense, pixel-level rewards from the hybrid data to serve as a localized signal and actively steer generation toward structurally reliable pixels. Finally, our model mitigates temporal shock by introducing thinking frames, a transition mechanism that seamlessly reconciles static image conditioning with dynamic video context. Extensive experiments demonstrate that our method prevents the corruption of multi-actor dynamics, establishing state-of-the-art spatiotemporal consistency, yielding consistent user preference (39% relative improvement in content preservation and 12% in temporal consistency), and achieving a significant 5% gain in downstream road line segmentation and 7% gain in downstream multi-object detection. Subjects: Computer Vision and Pattern Recognition (cs.CV) Cite as: arXiv:2610.28829 [cs.CV] (or arXiv:2610.28829v1 [cs.CV] for this version) https://doi.org/10.48550/arXiv.2610.28829 arXiv-issued DOI via DataCite (pending registration) Submission history From: Mauricio Soroco [view email] [v1] Tue, 20 Oct 2026 18:51:48 UTC (15,712 KB) Full-text links: Access Paper: View a PDF of the paper titled HorizonComposer: Spatiotemporally Consistent Driving Video Editing with Enriched Traffic Semantics, by Mauricio Soroco and 7 other authors View PDF HTML (experimental) TeX Source view license Additional Features Audio Summary Current browse context: cs.CV new | recent | 2026-10 Change to browse by: cs References & Citations SciX Google Scholar Semantic Scholar Loading... Data provided by: Bibliographic Tools Bibliographic and Citation Tools Bibliographic Explorer Toggle Bibliographic Explorer (What is the Explorer?) Connected Papers Toggle Connected Papers (What is Connected Papers?) Litmaps Toggle Litmaps (What is Litmaps?) scite.ai Toggle scite Smart Citations (What are Smart Citations?) Code, Data, Media Code, Data and Media Associated with this Article alphaXiv Toggle alphaXiv (What is alphaXiv?) Links to Code Toggle CatalyzeX Code Finder for Papers (What is CatalyzeX?) DagsHub Toggle DagsHub (What is DagsHub?) GotitPub Toggle Gotit.pub (What is GotitPub?) Huggingface Toggle Hugging Face (What is Huggingface?) ScienceCast Toggle ScienceCast (What is ScienceCast?) Demos Demos Replicate Toggle Replicate (What is Replicate?) Spaces Toggle Hugging Face Spaces (What is Spaces?) Spaces Toggle TXYZ.AI (What is TXYZ.AI?) Related Papers Recommenders and Search Tools Link to Influence Flower Influence Flower (What are Influence Flowers?) Core recommender toggle CORE Recommender (What is CORE?) Author Venue Institution Topic About arXivLabs arXivLabs: experimental projects with community collaborators arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website. Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them. Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs. Which authors of this paper are endorsers? | Disable MathJax (What is MathJax?)