PACER+: On-Demand Pedestrian Animation Controller in Driving Scenarios
Jingbo Wang, Zhengyi Luo, Ye Yuan, Yixuan Li, Bo Dai
摘要
a) Rich body control with trajectory and terrain compatibility (b) Zero-shot animation recreation from real-world videos (3) Missing Frame (1) Upper Body Motion (2) Whole Body Motion (1) (2) (3) Upper Body Reference Whole Body Reference Frame 15 Frame 22 Frame 60 Time Steps Figure 1 . We showcase the effectiveness of our proposed framework in synthetic and real-world driving scenarios. Our framework excels at generating physically realistic animations that adhere to provided trajectories while offering extensive control over the upper and full body movements. Additionally, our framework demonstrates the remarkable ability to recreate pedestrian animations with occlusions from real-world videos in a zero-shot manner. These inherent capabilities make our framework a robust and versatile approach foron-demand pedestrian animation in driving scenarios.
问问这篇 Paper
智能体会读完全文。
Lune 把这篇 Paper 索引到了每一个公式,引用它的顶会 Paper 也一样。你提问,回答直接引用原文。
引用它的顶会 Paper2
- HOSIG: Full-Body Human-Object-Scene Interaction Generation with Hierarchical Scene PerceptionWei Yao, Yunlian Sun, Hongwen Zhang, Yebin Liu 等AAAI 2026 · 被引用 4 次
- GPC: Large-Scale Generative Pretraining for Transferable Motor ControlYi Shi, Yifeng Jiang, Chen Tessler, Xue Bin PengSIGGRAPH 2026
它引用的顶会 Paper36
- Adding Conditional Control to Text-to-Image Diffusion ModelsLvmin Zhang, Anyi Rao, Maneesh AgrawalaICCV 2023 · 被引用 6,759 次
- AMASS: Archive of Motion Capture As Surface ShapesNaureen Mahmood, Nima Ghorbani, Nikolaus F. Troje, Gerard Pons-Moll 等ICCV 2019 · 被引用 1,784 次
- Learning to Reconstruct 3D Human Pose and Shape via Model-Fitting in the LoopNikos Kolotouros, Georgios Pavlakos, Michael J. Black, Kostas DaniilidisICCV 2019 · 被引用 1,139 次
- ViTPose: Simple Vision Transformer Baselines for Human Pose EstimationYufei Xu, Jing Zhang, Qiming Zhang, Dacheng TaoNeurIPS 2022 · 被引用 1,105 次
- Action-Conditioned 3D Human Motion Synthesis with Transformer VAEMathis Petrovich, Michael J. Black, Gül VarolICCV 2021 · 被引用 672 次
相关 Paper
- Trace and Pace: Controllable Pedestrian Animation via Guided Trajectory DiffusionDavis Rempe, Zhengyi Luo, Xue Bin Peng, Ye Yuan 等CVPR 2023
- Learning Human Dynamics in Autonomous Driving ScenariosJingbo Wang, Ye Yuan, Zhengyi Luo, Kevin Xie 等ICCV 2023 · 被引用 31 次
- Learning to Generate Diverse Pedestrian Movements from Web Videos with Noisy LabelsZhizheng Liu, Joe Lin, Wayne Wu, Bolei ZhouICLR 2025
- ActCam: Zero-Shot Joint Camera and 3D Motion Control for Video GenerationOmar El Khalifi, Thomas Rossi, Oscar Fossey, Thibault Fouque 等SIGGRAPH 2026
- S3: Neural Shape, Skeleton, and Skinning Fields for 3D Human ModelingZe Yang, Shenlong Wang, Sivabalan Manivasagam, Zeng Huang 等CVPR 2021
