DistScene：面向3D场景生成的对象到场景蒸馏
DistScene: Object-to-Scene Distillation for 3D Scene Generation
浏览论文内容
中文总结 AI 辅助
提出DistScene框架，通过显式建模环境组件、联合生成场景帧与对象、以对象为中心的细化及对象到场景蒸馏，实现单图像组合式3D场景生成，提升场景级空间一致性。
中文摘要 AI 辅助
我们提出了DistScene，一个通过联合建模环境和单个对象来实现单图像组合式3D场景生成的框架。与主要将场景表示为对象集合的现有方法不同，我们将环境建模为一个显式的场景组件，为对象放置提供几何上下文。具体来说，我们引入了场景帧生成（Scene-Frame Generation），在共享坐标帧中联合生成独立的环境和对象组件，使它们的几何和相对位置能够一起学习。然后，我们引入了以对象为中心的细化（Object-Centric Refinement），在局部帧中结合场景上下文细化每个对象。最后，我们开发了对象到场景蒸馏（Object-to-Scene Distillation），通过自动组合和渲染的合成场景，将预训练的对象生成先验迁移到场景生成中。在室内和室外基准上的评估表明，与评估的基线相比，场景级空间一致性有所提高。项目页面：此 https URL
英文摘要
We present DistScene, a framework for single-image compositional 3D scene generation by jointly modeling the environment and individual objects. Unlike existing methods that represent scenes primarily as collections of objects, we model the environment as an explicit scene component to provide geometric context for object placement. Specifically, we introduce Scene-Frame Generation, which jointly generates separate environment and object components in a shared coordinate frame, allowing their geometry and relative placement to be learned together. Then we introduce Object-Centric Refinement to refine each object in a local frame with scene context. Finally, we develop Object-to-Scene Distillation to transfer pretrained object-generation priors to scene generation through automatically composed and rendered synthetic scenes. Evaluations on indoor and outdoor benchmarks demonstrate improved scene-level spatial coherence over the evaluated baselines. Project page: https://coolbeam.github.io/DistScene/
发表机构
- The Hong Kong University of Science and Technology（香港科技大学）
- TeleAI, China Telecom（中国电信TeleAI）
机构由 AI 辅助整理，请以论文原文为准。
