Sitcom-Crafter: A Plot-Driven Human Motion Generation System in 3D Scenes
Not on the map. Why?
Abstract (arXiv)
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.
Key facts. Cited by 14 papers in the map (data through 14 Oct 2026). Builds on 35 of its 45 references that are in the map. First posted on arXiv 14 Oct 2024.
Builds on
35 of 45 references.
References · 35
- 2021Learning Transferable Visual Models From Natural Language Supervisioncited by 33,744
- 2023GPT-4 Technical Reportcited by 18,396
- 2017Proximal Policy Optimization Algorithmscited by 15,215
- 2022Scalable Diffusion Models with Transformerscited by 6,054
- 2024Gemini 1.5: Unlocking multimodal understanding across millions of tokens of contextcited by 3,224
- 2019Expressive Body Capture: 3D Hands, Face, and Body from a Single Imagecited by 1,612
- 2022Human Motion Diffusion Modelcited by 1,080
- 2019The Replica Dataset: A Digital Replica of Indoor Spacescited by 904
- 2023MotionGPT: Human Motion as a Foreign Languagecited by 527
- 2021Action-Conditioned 3D Human Motion Synthesis with Transformer VAEcited by 501
- 2021AI Choreographer: Music Conditioned 3D Dance Generation with AIST++cited by 485
- 2022PhysDiff: Physics-Guided Human Motion Diffusion Modelcited by 368
23 more
- 2023Human Motion Diffusion as a Generative Priorcited by 357
- 2017On human motion prediction using recurrent neural networkscited by 338
- 2020Monocular, One-stage, Regression of Multiple 3D Peoplecited by 218
- 2023Object Motion Guided Human Motion Synthesiscited by 212
- 2023InterGen: Diffusion-based Multi-human Motion Generation under Complex Interactionscited by 206
- 2023InterDiff: Generating 3D Human-Object Interactions with Physics-Informed Diffusioncited by 182
- 2017HP-GAN: Probabilistic 3D human motion prediction via GANcited by 176
- 2022TEACH: Temporal Action Composition for 3D Humanscited by 176
- 2020Populating 3D Scenes by Learning Human-Scene Interactioncited by 164
- 2024Scaling Up Dynamic Human-Scene Interaction Modelingcited by 137
- 2019Generating 3D People in Scenes without Peoplecited by 127
- 2023Synthesizing Diverse Human Motions in 3D Indoor Scenescited by 109
- 2023Inter-X: Towards Versatile Human-Human Interaction Analysiscited by 98
- 2023Unified Human-Scene Interaction via Prompted Chain-of-Contactscited by 94
- 2018MT-VAE: Learning Motion Transformations to Generate Multimodal Human Dynamicscited by 86
- 2022Compositional Human-Scene Interaction Synthesis with Semantic Controlcited by 83
- 2019You2Me: Inferring Body Pose in Egocentric Video via First and Second Person Interactionscited by 82
- 2019Putting Humans in a Scene: Learning Affordance in 3D Indoor Environmentscited by 72
- 2021The Wanderings of Odysseus in 3D Scenescited by 59
- 2023Generative Proxemics: A Prior for 3D Social Interaction from Imagescited by 43
- 2023Digital Life Project: Autonomous 3D Characters with Social Intelligencecited by 43
- 2023Generating Continual Human Motion in Diverse 3D Scenescited by 39
- 2022Placing Human Animations into 3D Scenes by Learning Interaction- and Geometry-Driven Keyframescited by 8
Built on by
Citing papers per year: 2024: 1; 2025: 9; 2026: 4.
14 papers.
Sort:
By area:
- 2024Rethinking Diffusion for Text-Driven Human Motion Generation: Redundant Representations, Evaluation, and Masked Autoregressioncited by 85
- 2025Absolute Coordinates Make Motion Generation Easycited by 29
- 2025A Survey on Human Interaction Motion Generationcited by 25
- 20253D Human Interaction Generation: A Surveycited by 7
- 2025HIS-GPT: Towards 3D Human-In-Scene Multimodal Understandingcited by 6
- 2025PhysiInter: Integrating Physical Mapping for High-Fidelity Human Interaction Generationcited by 4
- 2025Event-Driven Storytelling with Multiple Lifelike Humans in a 3D Scenecited by 4
- 2026InfBaGel: Human-Object-Scene Interaction Generation with Dynamic Perception and Iterative Refinementcited by 3
- 2026Dynamic Worlds, Dynamic Humans: Generating Virtual Human-Scene Interaction Motion in Dynamic Scenescited by 2
- 2026ReMoGen: Real-time Human Interaction-to-Reaction Generation via Modular Learning from Diverse Datacited by 1
- 2025BridgeIV: Bridging Customized Image and Video Generation through Test-Time Autoregressive Identity Propagationcited by 0
- 2025FantasyHSI: Video-Generation-Centric 4D Human Synthesis In Any Scene through A Graph-based Multi-Agent Frameworkcited by 0
- 2026ARMS: Anchor-Relational Motion Streaming for Seamless Solo-Social Motion Transitions7 Jul 2026
- 2026InfBaGel: Human-Object-Scene Interaction Generation with Dynamic Perception and Iterative Refinement6 Apr 2026
- 2026ReMoGen: Real-time Human Interaction-to-Reaction Generation via Modular Learning from Diverse Data1 Apr 2026
- 2026Dynamic Worlds, Dynamic Humans: Generating Virtual Human-Scene Interaction Motion in Dynamic Scenes27 Jan 2026
- 2025BRIC: Bridging Kinematic Plans and Physical Control at Test Time25 Nov 2025
- 2025FantasyHSI: Video-Generation-Centric 4D Human Synthesis In Any Scene through A Graph-based Multi-Agent Framework1 Sep 2025
- 2025Event-Driven Storytelling with Multiple Lifelike Humans in a 3D Scene25 Jul 2025
- 2025PhysiInter: Integrating Physical Mapping for High-Fidelity Human Interaction Generation9 Jun 2025
- 2025Absolute Coordinates Make Motion Generation Easy26 May 2025
- 2025BridgeIV: Bridging Customized Image and Video Generation through Test-Time Autoregressive Identity Propagation11 May 2025
- 20253D Human Interaction Generation: A Survey17 Mar 2025
- 2025HIS-GPT: Towards 3D Human-In-Scene Multimodal Understanding17 Mar 2025
- 2024Rethinking Diffusion for Text-Driven Human Motion Generation: Redundant Representations, Evaluation, and Masked Autoregressioncited by 85
- 2025Absolute Coordinates Make Motion Generation Easycited by 29
- 2025A Survey on Human Interaction Motion Generationcited by 25
- 20253D Human Interaction Generation: A Surveycited by 7
- 2025HIS-GPT: Towards 3D Human-In-Scene Multimodal Understandingcited by 6
- 2025PhysiInter: Integrating Physical Mapping for High-Fidelity Human Interaction Generationcited by 4
- 2025Event-Driven Storytelling with Multiple Lifelike Humans in a 3D Scenecited by 4
- 2026Dynamic Worlds, Dynamic Humans: Generating Virtual Human-Scene Interaction Motion in Dynamic Scenescited by 2
- 2026ReMoGen: Real-time Human Interaction-to-Reaction Generation via Modular Learning from Diverse Datacited by 1
- 2025BridgeIV: Bridging Customized Image and Video Generation through Test-Time Autoregressive Identity Propagationcited by 0
- 2025FantasyHSI: Video-Generation-Centric 4D Human Synthesis In Any Scene through A Graph-based Multi-Agent Frameworkcited by 0
- 2026ARMS: Anchor-Relational Motion Streaming for Seamless Solo-Social Motion Transitionscited by 0
- 2026ARMS: Anchor-Relational Motion Streaming for Seamless Solo-Social Motion Transitions7 Jul 2026
- 2026ReMoGen: Real-time Human Interaction-to-Reaction Generation via Modular Learning from Diverse Data1 Apr 2026
- 2026Dynamic Worlds, Dynamic Humans: Generating Virtual Human-Scene Interaction Motion in Dynamic Scenes27 Jan 2026
- 2025FantasyHSI: Video-Generation-Centric 4D Human Synthesis In Any Scene through A Graph-based Multi-Agent Framework1 Sep 2025
- 2025Event-Driven Storytelling with Multiple Lifelike Humans in a 3D Scene25 Jul 2025
- 2025PhysiInter: Integrating Physical Mapping for High-Fidelity Human Interaction Generation9 Jun 2025
- 2025Absolute Coordinates Make Motion Generation Easy26 May 2025
- 2025BridgeIV: Bridging Customized Image and Video Generation through Test-Time Autoregressive Identity Propagation11 May 2025
- 20253D Human Interaction Generation: A Survey17 Mar 2025
- 2025HIS-GPT: Towards 3D Human-In-Scene Multimodal Understanding17 Mar 2025
- 2025A Survey on Human Interaction Motion Generation17 Mar 2025
- 2024Rethinking Diffusion for Text-Driven Human Motion Generation: Redundant Representations, Evaluation, and Masked Autoregression25 Nov 2024