Lune

ICLR2025顶会

Sitcom-Crafter: A Plot-Driven Human Motion Generation System in 3D Scenes

Jianqi Chen, Panwen Hu, Xiaojun Chang, Zhenwei Shi, Michael Kampffmeyer, Xiaodan Liang

摘要

Recent advancements in human motion synthesis have focused on specific types of motions, such as human-scene interaction, locomotion or human-human interaction, however, there is a lack of a unified system capable of generating a diverse combination of motion types. In response, we introduce Sitcom-Crafter, a comprehensive and extendable system for human motion generation in 3D space, which can be guided by extensive plot contexts to enhance workflow efficiency for anime and game designers. The system is comprised of eight modules, three of which are dedicated to motion generation, while the remaining five are augmentation modules that ensure consistent fusion of motion sequences and system functionality. Central to the generation modules is our novel 3D scene-aware human-human interaction module, which addresses collision issues by synthesizing implicit 3D Signed Distance Function (SDF) points around motion spaces, thereby minimizing human-scene collisions without additional data collection costs. Complementing this, our locomotion and human-scene interaction modules leverage existing methods to enrich the system's motion generation capabilities. Augmentation modules encompass plot comprehension for command generation, motion synchronization for seamless integration of different motion types, hand pose retrieval to enhance motion realism, motion collision revision to prevent human collisions, and 3D retargeting to ensure visual fidelity. Experimental evaluations validate the system's ability to generate high-quality, diverse, and physically realistic motions, underscoring its potential for advancing creative workflows. Project page: https://windvchen.github.io/Sitcom-Crafter.

问 Lune

尽管问,回答会引用原文。

Lune 会读完全文和相关的 Paper,每个回答都附上所依据的原文段落。

可以从这些问题问起

Lune 的依据

全文 · 引用它的 10 篇顶会 Paper · 相关的 Paper

获取答案

免费开始,无需绑卡

引用它的顶会 Paper10

  1. HIS-GPT: Towards 3D Human-In-Scene Multimodal UnderstandingJiahe Zhao, Ruibing Hou, Zejie Tian, Hong Chang 等ICCV 2025 · 6 次引用
  2. InfBaGel: Human-Object-Scene Interaction Generation with Dynamic Perception and Iterative RefinementYude Zou, Junji Gong, Xing Gao, Zixuan Li 等ICLR 2026 · 3 次引用
  3. ReMoGen: Real-time Human Interaction-to-Reaction Generation via Modular Learning from Diverse DataYaoqin Ye, Yiteng Xu, Qin Sun, Xinge Zhu 等CVPR 2026 · 2 次引用
  4. Dynamic Worlds, Dynamic Humans: Generating Virtual Human-Scene Interaction Motion in Dynamic ScenesYin Wang, Zhiying Leng, Haitian Liu, Frederick W. B. Li 等IEEE VR 2026 · 1 次引用
  5. Unified Multi-Agent Trajectory Modeling with Masked Trajectory DiffusionSongru Yang, Zhenwei Shi, Zhengxia ZouICCV 2025 · 1 次引用

它引用的 Paper24

  1. Learning Transferable Visual Models From Natural Language SupervisionAlec Radford, Jong Wook Kim, Chris Hallacy, Aditya Ramesh 等ICML 2021 · 47,906 次引用
  2. High-Resolution Image Synthesis with Latent Diffusion ModelsRobin Rombach, Andreas Blattmann, Dominik Lorenz, Patrick Esser 等CVPR 2022 · 13,123 次引用
  3. Scalable Diffusion Models with TransformersWilliam Peebles, Saining XieICCV 2023 · 5,568 次引用
  4. AI Choreographer: Music Conditioned 3D Dance Generation with AIST++Ruilong Li, Shan Yang, David A. Ross, Angjoo KanazawaICCV 2021 · 701 次引用
  5. MotionGPT: Human Motion as a Foreign LanguageBiao Jiang, Xin Chen, Wen Liu, Jingyi Yu 等NeurIPS 2023 · 698 次引用

相关 Paper

  1. InterPhys: Physics-aware Human Motion Synthesis in a Dynamic SceneChaoyue Xing, Wei Mao, Miaomiao LiuCVPR 2026 · 1 次引用
  2. Synthesizing Diverse Human Motions in 3D Indoor ScenesKaifeng Zhao, Yan Zhang, Shaofei Wang, Thabo Beeler 等ICCV 2023 · 116 次引用
  3. Towards Diverse and Natural Scene-aware 3D Human Motion SynthesisJingbo Wang, Yu Rong, Jingyuan Liu, Sijie Yan 等CVPR 2022 · 74 次引用
  4. SemGeoMo: Dynamic Contextual Human Motion Generation with Semantic and Geometric GuidancePeishan Cong, Ziyi Wang, Yuexin Ma, Xiangyu YueCVPR 2025
  5. Synthesizing Long-Term 3D Human Motion and Interaction in 3D ScenesJiashun Wang, Huazhe Xu, Jingwei Xu, Sifei Liu 等CVPR 2021
黄昏的海面,两侧是细线勾勒的悬崖