ReConText3D: 基于重放的持续文本到3D生成
ReConText3D: Replay-based Continual Text-to-3D Generation
AI总结：
本文提出ReConText3D框架，解决文本到3D生成中的持续学习问题，通过文本嵌入k-Center选择构建紧凑多样回放记忆，实现增量学习新3D类别并保持旧类生成能力。
摘要：
持续学习使模型能够随时间获取新知识同时保留先前学习能力。然而，其在文本到3D生成中的应用仍无先例。我们提出了ReConText3D，首个持续文本到3D生成框架。我们首先证明现有文本到3D模型在增量训练下存在灾难性遗忘。ReConText3D使生成模型能够逐步学习新3D类别，同时保持合成先前资产的能力。我们的方法通过文本嵌入k-Center选择构建紧凑且多样化的回放记忆，允许在不修改底层架构的情况下进行代表性复习。为系统评估持续文本到3D学习，我们引入Toys4K-CL基准，源自Toys4K数据集，提供平衡且语义多样的类别增量分割。在Toys4K-CL基准上的广泛实验表明，ReConText3D在不同生成底层架构下均优于所有基线，保持对旧类和新类的高质量生成。到目前为止，这项工作建立了首个文本到3D生成的持续学习框架和基准，为增量3D生成建模开辟了新方向。项目页面可在：https://mauk95.github.io/ReConText3D/
英文摘要：
Continual learning enables models to acquire new knowledge over time while retaining previously learned capabilities. However, its application to text-to-3D generation remains unexplored. We present ReConText3D, the first framework for continual text-to-3D generation. We first demonstrate that existing text-to-3D models suffer from catastrophic forgetting under incremental training. ReConText3D enables generative models to incrementally learn new 3D categories from textual descriptions while preserving the ability to synthesize previously seen assets. Our method constructs a compact and diverse replay memory through text-embedding k-Center selection, allowing representative rehearsal of prior knowledge without modifying the underlying architecture. To systematically evaluate continual text-to-3D learning, we introduce Toys4K-CL, a benchmark derived from the Toys4K dataset that provides balanced and semantically diverse class-incremental splits. Extensive experiments on the Toys4K-CL benchmark show that ReConText3D consistently outperforms all baselines across different generative backbones, maintaining high-quality generation for both old and new classes. To the best of our knowledge, this work establishes the first continual learning framework and benchmark for text-to-3D generation, opening a new direction for incremental 3D generative modeling. Project page is available at: https://mauk95.github.io/ReConText3D/.
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。
