[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"item-2519":3},{"id":4,"title":5,"url":6,"summary":7,"summary_zh":8,"content":9,"source_name":10,"source_url":6,"published_at":11,"category":12,"cover_url":9,"hotness":13,"is_selected":14,"score":15,"score_detail":16,"sources":23,"tags":25,"view_count":31,"doi":32,"paper":33,"created_at":52},2519,"OneGrow: Unified Temporal Plant Image and Mask Generation","https:\u002F\u002Fdoi.org\u002F10.64898\u002F2026.09.11.750899","Image-based crop phenotyping benefits from image series that capture plant development together with organ-level labels. Such paired data are limited because organ annotation is expensive, and following the same plants over time requires repeated, registered imaging. Existing generative models for plants either synthesize temporal imagery without structural labels or generate labeled images without a temporal dimension. We introduce OneGrow, a latent flow-matching model that jointly models wheat images and their organ-segmentation masks over time. Images and masks share a single frozen image autoencoder. A reveal specifies which content is observed context, so the same model covers tasks such as mask-to-image synthesis, image-to-mask segmentation, and temporal forecasting. For sequences longer than the training window, a sliding-window roll-out generates each new image from the preceding frames, keeping long sequences temporally consistent. We train jointly on a large single-frame wheat dataset and a multi-year temporal dataset, using pseudo-labels from a pretrained segmentation model. We evaluate segmentation and image quality against held-out references and assess the multi-task and temporal behavior qualitatively.","基于图像的作物表型分析受益于能够同时捕捉植物发育过程与器官级标签的图像序列。此类配对数据较为有限，因为器官标注成本高昂，且对同一植株进行长期追踪需要重复的配准成像。现有的植物生成模型要么合成不具备结构标签的时间序列图像，要么生成不具备时间维度的标注图像。我们提出OneGrow，一种潜在流匹配模型，可联合建模小麦图像及其器官分割掩码随时间的演变。图像与掩码共享一个冻结的图像自编码器。通过指定哪些内容作为观测上下文，同一模型即可覆盖掩码到图像合成、图像到掩码分割以及时间预测等任务。对于超出训练窗口的序列，采用滑动窗口展开方式，由前序帧生成每一新图像，从而保持长序列的时间一致性。我们在一个大型单帧小麦数据集和一个多年时间数据集上进行联合训练，使用预训练分割模型生成的伪标签。我们以留出参考数据评估分割和图像质量，并定性评估多任务与时间行为。",null,"bioRxiv (Cold Spring Harbor Laboratory)","2026-09-14T00:00:00Z","论文",10,false,78,{"impact":17,"substance":18,"depth":17,"authority":19,"freshness":20,"relevant":21,"comment":22},18,21,13,8,1,"面向小麦时序图像与器官分割掩码联合生成的流匹配模型，方法新颖、数据规模可观，对作物表型自动化标注有实质推动，值得进入每日精选。",[24],{"name":10,"url":6},[26,27,28,29,30],"智慧农业","农业人工智能","小麦","作物表型","图像生成",0,"10.64898\u002F2026.09.11.750899",{"doi":32,"openalex_id":34,"authors":35,"venue":10,"cited_by_count":31,"oa_url":6,"card":45,"direction":49,"ingested_from":51},"W7212556016",[36,39,42],{"name":37,"orcid":38},"Mike Boss","https:\u002F\u002Forcid.org\u002F0000-0002-7234-3796",{"name":40,"orcid":41},"Michele Volpi","https:\u002F\u002Forcid.org\u002F0000-0003-2771-0750",{"name":43,"orcid":44},"Lukas Roth","https:\u002F\u002Forcid.org\u002F0000-0003-1435-9535",{"tldr":46,"method":47,"finding":48,"direction":49,"opportunity":50},"提出OneGrow模型，联合生成小麦时序图像与器官分割掩码。","潜在流匹配模型，共享冻结自编码器，滑动窗口滚动生成。","同一模型可完成掩码到图像、图像分割和时序预测，保持长序列一致。","农业遥感与作物表型","可探索多作物、多器官的时序联合生成，降低表型标注成本。","openalex","2026-09-15T23:30:15.715938Z"]