Tstars-Tryon 1.0：鲁棒且逼真的虚拟试衣系统用于多样化服装物品
Tstars-Tryon 1.0: Robust and Realistic Virtual Try-On for Diverse Fashion Items
AI总结：
本文提出Tstars-Tryon 1.0，一种高效且逼真的虚拟试衣系统，能够处理复杂场景，支持多件衣物试穿，并在大规模部署中实现高效率和高质量输出。
摘要：
近年来，图像生成和编辑技术的进步为虚拟试衣提供了新机遇。然而，现有方法仍难以满足复杂现实需求。我们提出了Tstars-Tryon 1.0，一个商业级虚拟试衣系统，具有鲁棒性、逼真性、多样性及高效率。首先，系统在极端姿势、严重光照变化、运动模糊等野外条件下保持高成功率。其次，它能生成高度逼真的结果，保留衣物纹理、材料属性和结构特征，同时避免常见AI生成伪影。第三，系统不仅支持衣物试穿，还支持灵活的多图合成（最多6张参考图），覆盖8类时尚品类，协调控制人物身份和背景。第四，为克服商业部署的延迟瓶颈，系统通过优化推理速度，实现接近实时的生成，提供无缝用户体验。这些能力由端到端模型架构、可扩展的数据引擎、稳健的基础设施和多阶段训练范式组成。大量评估和大规模产品部署证明Tstars-Tryon 1.0整体性能领先。为支持未来研究，我们还发布了综合基准。该模型已部署在淘宝App上，服务于数百万用户，处理数千万次请求。
英文摘要：
Recent advances in image generation and editing have opened new opportunities for virtual try-on. However, existing methods still struggle to meet complex real-world demands. We present Tstars-Tryon 1.0, a commercial-scale virtual try-on system that is robust, realistic, versatile, and highly efficient. First, our system maintains a high success rate across challenging cases like extreme poses, severe illumination variations, motion blur, and other in-the-wild conditions. Second, it delivers highly photorealistic results with fine-grained details, faithfully preserving garment texture, material properties, and structural characteristics, while largely avoiding common AI-generated artifacts. Third, beyond apparel try-on, our model supports flexible multi-image composition (up to 6 reference images) across 8 fashion categories, with coordinated control over person identity and background. Fourth, to overcome the latency bottlenecks of commercial deployment, our system is heavily optimized for inference speed, delivering near real-time generation for a seamless user experience. These capabilities are enabled by an integrated system design spanning end-to-end model architecture, a scalable data engine, robust infrastructure, and a multi-stage training paradigm. Extensive evaluation and large-scale product deployment demonstrate that Tstars-Tryon1.0 achieves leading overall performance. To support future research, we also release a comprehensive benchmark. The model has been deployed at an industrial scale on the Taobao App, serving millions of users with tens of millions of requests.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
