面向检测、分割与视觉定位的可扩展精确学习的合成物体组合
Synthetic Object Compositions for Scalable and Accurate Learning in Detection, Segmentation, and Grounding
用 3D 几何布局与相机配置增强把高质量物体片段合成为带精确掩码、框和指代表达的训练图像，可直接替代或补充 LVIS/COCO 等真实标注数据，尤其适合低数据量与细粒度属性判别场景。
原文依据 We introduce SOC, an accurate and scalable data synthesis pipeline via a novel object-centric composition strategy.
摘要译文
由模型翻译 · 术语统一 · 请对照原文核对关键结论视觉分组——通过实例分割、视觉定位和目标检测等任务加以操作化——支撑着从机器人感知到照片编辑的各类应用。这些计算机视觉中的基础问题由大规模、需精心标注的数据集驱动。尽管影响巨大，这些数据集构建成本高昂、覆盖存在偏差且难以扩展。合成数据集提供了有前景的替代方案，但在灵活性、准确性和组合多样性方面仍存在困难。我们提出 SOC，一种通过新颖的以物体为中心的组合策略实现的精确且可扩展的数据合成流水线。它利用 3D 几何布局增强与相机配置增强，并结合生成式协调与掩码面积加权混合，将高质量的合成物体片段组合成新图像，从而产生准确且多样的掩码、边界框和指代表达。仅在 10 万张我们的合成图像上训练的模型，其表现优于在更大规模真实数据集（GRIT 20M、V3Det 200K）和合成流水线（Copy-Paste、X-Paste、SynGround、SegGen，提升 24–36%）上训练的模型——在 LVIS 上取得 +10.9 AP，在 gRefCOCO 上取得 +8.4 NAcc。SOC 还能针对不同用例实现可控的数据集构建，并在低数据量和闭词表场景下提升性能。用合成物体片段增强 LVIS 和 COCO，可在不同真实数据规模下带来强劲性能，而当真实数据极为有限时提升更为显著（在 1% COCO 数据上 +6.59 AP）。此外，这种可控性使得针对类内指代的定向数据生成成为可能，这是我们提出的一个需要细粒度属性判别的诊断性视觉定位任务。
英文原文摘要 1719 字符
Visual grouping--operationalized through tasks such as instance segmentation, visual grounding, and object detection--enables applications ranging from robotic perception to photo editing. These fundamental problems in computer vision are powered by large-scale, painstakingly annotated datasets. Despite their impact, these datasets are costly to build, biased in coverage, and difficult to scale. Synthetic datasets offer a promising alternative but struggle with flexibility, accuracy, and compositional diversity. We introduce SOC, an accurate and scalable data synthesis pipeline via a novel object-centric composition strategy. It composes high-quality synthetic object segments into new images using 3D geometric layout augmentation and camera configuration augmentation with generative harmonization and mask-area-weighted blending, yielding accurate and diverse masks, boxes, and referring expressions. Models trained on just 100K of our synthetic images outperform those trained on larger real datasets (GRIT 20M, V3Det 200K) and synthetic pipelines (Copy-Paste, X-Paste, SynGround, SegGen by +24-36%)--achieving +10.9 AP on LVIS and +8.4 NAcc on gRefCOCO. SOC also enables controllable dataset construction for different use cases and boosts performance in both low-data and closed-vocabulary scenarios. Augmenting LVIS and COCO with synthetic object segments delivers strong performance across different real data scales and yields even greater improvements when real data is extremely limited (+6.59 AP on 1% COCO data). Furthermore, this controllability enables targeted data generation for intra-class referring, a diagnostic grounding task we propose that requires fine-grained attribute discrimination.