mlsanityData to 14 Oct 2026

PACER+: On-Demand Pedestrian Animation Controller in Driving Scenarios

arXiv 2404.19722 ↗First posted 30 Apr 2024cs.CVcited by 24

Not on the map. Why?

Abstract (arXiv)

We address the challenge of content diversity and controllability in pedestrian simulation for driving scenarios. Recent pedestrian animation frameworks have a significant limitation wherein they primarily focus on either following trajectory [46] or the content of the reference video [57], consequently overlooking the potential diversity of human motion within such scenarios. This limitation restricts the ability to generate pedestrian behaviors that exhibit a wider range of variations and realistic motions and therefore restricts its usage to provide rich motion content for other components in the driving simulation system, e.g., suddenly changed motion to which the autonomous vehicle should respond. In our approach, we strive to surpass the limitation by showcasing diverse human motions obtained from various sources, such as generated human motions, in addition to following the given trajectory. The fundamental contribution of our framework lies in combining the motion tracking task with trajectory following, which enables the tracking of specific motion parts (e.g., upper body) while simultaneously following the given trajectory by a single policy. This way, we significantly enhance both the diversity of simulated human motion within the given scenario and the controllability of the content, including language-based control. Our framework facilitates the generation of a wide range of human motions, contributing to greater realism and adaptability in pedestrian simulations for driving scenarios. More information is on our project page https://wangjingbo1219.github.io/papers/CVPR2024_PACER_PLUS/PACERPLUSPage.html .

Key facts. Cited by 24 papers in the map (data through 14 Oct 2026). Builds on 65 of its 87 references that are in the map. First posted on arXiv 30 Apr 2024.

Builds on

65 of 87 references.

References · 65

  1. 2017Proximal Policy Optimization Algorithmscited by 15,215
  2. 2023Adding Conditional Control to Text-to-Image Diffusion Modelscited by 5,503
  3. 2019AMASS: Archive of Motion Capture as Surface Shapescited by 1,236
  4. 2018On the Continuity of Rotation Representations in Neural Networkscited by 1,214
  5. 2022Human Motion Diffusion Modelcited by 1,080
  6. 2017End-to-end Recovery of Human Shape and Posecited by 885
  7. 2019Learning to Reconstruct 3D Human Pose and Shape via Model-fitting in the Loopcited by 627
  8. 2019VIBE: Video Inference for Human Body Pose and Shape Estimationcited by 620
  9. 2022Executing your Commands via Motion Diffusion in Latent Spacecited by 575
  10. 2021Action-Conditioned 3D Human Motion Synthesis with Transformer VAEcited by 501
  11. 2022ViTPose: Simple Vision Transformer Baselines for Human Pose Estimationcited by 456
  12. 20183D human pose estimation in video with temporal convolutions and semi-supervised trainingcited by 403
38 more
  1. 2022PhysDiff: Physics-Guided Human Motion Diffusion Modelcited by 368
  2. 2021HuMoR: 3D Human Motion Model for Robust Pose Estimationcited by 324
  3. 2020HybrIK: A Hybrid Analytical-Neural Inverse Kinematics Solution for 3D Human Pose and Shape Estimationcited by 307
  4. 2018Learning to Estimate 3D Human Pose and Shape from a Single Color Imagecited by 226
  5. 2023Perpetual Humanoid Control for Real-time Simulated Avatarscited by 218
  6. 2017Unite the People: Closing the Loop Between 3D and 2D Human Representationscited by 205
  7. 2017Single-Shot Multi-Person 3D Pose Estimation From Monocular RGBcited by 195
  8. 2021TrafficSim: Learning to Simulate Realistic Multi-Agent Behaviorscited by 193
  9. 2023MatrixCity: A Large-scale City Dataset for City-scale Neural Rendering and Beyondcited by 185
  10. 2021Character Controllers Using Motion VAEscited by 184
  11. 2018DeepMimic: Example-Guided Deep Reinforcement Learning of Physics-Based Character Skillscited by 163
  12. 2021GLAMR: Global Occlusion-Aware Human Mesh Recovery with Dynamic Camerascited by 153
  13. 2021Generating Useful Accident-Prone Driving Scenarios via a Learned Traffic Priorcited by 139
  14. 2023Trace and Pace: Controllable Pedestrian Animation via Guided Trajectory Diffusioncited by 138
  15. 2019Camera Distance-aware Top-down Approach for 3D Multi-person Pose Estimation from a Single RGB Imagecited by 132
  16. 2017VNect: Real-time 3D Human Pose Estimation with a Single RGB Cameracited by 129
  17. 2023Universal Humanoid Motion Representations for Physics-Based Controlcited by 116
  18. 2021SimPoE: Simulated Character Control for 3D Human Pose Estimationcited by 114
  19. 2020Exemplar Fine-Tuning for 3D Human Model Fitting Towards In-the-Wild 3D Human Pose Estimationcited by 113
  20. 2019Exploiting temporal context for 3D human pose estimation in the wildcited by 110
  21. 2019MCP: Learning Composable Hierarchical Control with Multiplicative Compositional Policiescited by 108
  22. 2021Dynamics-Regulated Kinematic Policy for Egocentric Pose Estimationcited by 101
  23. 2020Contact and Human Dynamics from Monocular Videocited by 95
  24. 2023CALM: Conditional Adversarial Latent Models for Directable Virtual Characterscited by 94
  25. 2023TLControl: Trajectory and Language Control for Human Motion Synthesiscited by 94
  26. 2017Towards Accurate Markerless Human Shape and Pose Estimation over Timecited by 92
  27. 2023EMDM: Efficient Motion Diffusion Model for Fast and High-Quality Motion Generationcited by 89
  28. 2019Ego-Pose Estimation and Forecasting as Real-Time PD Controlcited by 87
  29. 2019Human Mesh Recovery from Monocular Images via a Skeleton-disentangled Representationcited by 87
  30. 2020Learning to Generate Diverse Dance Motions with Transformercited by 85
  31. 2020Human Body Model Fitting by Learned Gradient Descentcited by 81
  32. 2021GeoSim: Realistic Video Simulation via Geometry-Aware Composition for Self-Drivingcited by 75
  33. 2021Neural Monocular 3D Human Motion Capture with Physical Awarenesscited by 71
  34. 2021Physics-based Human Motion Estimation and Synthesis from Videoscited by 66
  35. 2020Residual Force Control for Agile Human Behavior Imitation and Extended Motion Synthesiscited by 64
  36. 2023MoConVQ: Unified Physics-Based Motion Control via Scalable Discrete Representationscited by 60
  37. 2023C·ASE: Learning Conditional Adversarial Skill Embeddings for Physics-based Characterscited by 55
  38. 2020PhysCap: Physically Plausible Monocular 3D Motion Capture in Real Timecited by 50

50 most cited of 65 All 65 (JSON)

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2024: 7; 2025: 13; 2026: 4.

24 papers.

Sort:

By area:

  1. 2024OmniRe: Omni Urban Scene Reconstructioncited by 161
  2. 2024MaskedMimic: Unified Physics-Based Character Control Through Masked Motion Inpaintingcited by 116
  3. 2025TokenHSI: Unified Synthesis of Physical Human-Scene Interactions through Task Tokenizationcited by 51
  4. 2025UniPhys: Unified Planner and Controller with Diffusion for Flexible Physics-Based Character Controlcited by 25
  5. 2024Lodge++: High-quality and Long Dance Generation with Vivid Choreography Patternscited by 21
  6. 2024Mimicking-Bench: A Benchmark for Generalizable Humanoid-Scene Interaction Learning via Human Mimickingcited by 16
  7. 2025PRIMAL: Physically Reactive and Interactive Motor Model for Avatar Learningcited by 14
  8. 2025Reconstructing 4D Spatial Intelligence: A Surveycited by 14
  9. 2025Physical Plausibility-aware Trajectory Prediction via Locomotion Embodimentcited by 10
  10. 2025ModSkill: Physical Character Skill Modularizationcited by 7
  11. 2024A Plug-and-Play Physical Motion Restoration Approach for In-the-Wild High-Difficulty Motionscited by 5
  12. 2025HOSIG: Full-Body Human-Object-Scene Interaction Generation with Hierarchical Scene Perceptioncited by 5
12 more
  1. 2025InterAgent: Physics-based Multi-agent Command Execution via Diffusion on Interaction Graphscited by 5
  2. 2024Learning to Generate Diverse Pedestrian Movements from Web Videos with Noisy Labelscited by 4
  3. 2025CBIL: Collective Behavior Imitation Learning for Fish from Real Videoscited by 4
  4. 2024ChatDyn: Language-Driven Multi-Actor Dynamics Generation in Street Scenescited by 3
  5. 2025LangDriveCTRL: Natural Language Controllable Driving Scene Editing with Multi-modal Agentscited by 3
  6. 2026QuaMo: Quaternion Motions for Vision-based 3D Human Kinematics Capturecited by 3
  7. 2025Jointly Understand Your Command and Intention:Reciprocal Co-Evolution between Scene-Aware 3D Human Motion Synthesis and Analysiscited by 2
  8. 2026Flow Matching for Probabilistic Monocular 3D Human Pose Estimationcited by 2
  9. 2025RESCUE: Crowd Evacuation Simulation via Controlling SDM-United Characterscited by 1
  10. 2025HABIT: Human Action Benchmark for Interactive Traffic in CARLAcited by 1
  11. 2026NaP-Control: Navigating Diffusion Prior for Versatile and Fast Character Controlcited by 0
  12. 2026MTF-Net: Multi-Modal Temporal Feature Fusion Network for Pedestrian Intention Predictioncited by 0