Nonisotropic Gaussian Diffusion for Realistic 3D Human Motion Prediction
Cecilia Curreli, Dominik Muhle, Abhishek Saroha, Zhenzhang Ye, Riccardo Marin, Daniel Cremers
2025年份
6顶会引用
摘要
P as t G T F u tu re P re d ic te d fu tu re s C lo se st D iv er se #1 D iv er se #2 D iv er se #3 Figure 1. SkeletonDiffusion generates futures that are simultaneously diverse and realistic. With a nonisotropic diffusion formulation reflecting the skeleton structure, we predict motions that are plausible and semantically coherent with the input past while being highly diverse. Here, we show the most diverse ensemble of three motions including the prediction closest to the ground truth among 50 generated futures.
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 Paper6
- Noise Hypernetworks: Amortizing Test-Time Compute in Diffusion ModelsLuca Eyring, Shyamgopal Karthik, Alexey Dosovitskiy, Nataniel Ruiz 等NeurIPS 2025 · 被引用 36 次
- mmPred: Radar-based Human Motion Prediction in the DarkJunqiao Fan, Haocong Rao, Jiarui Zhang, Jianfei Yang 等AAAI 2026 · 被引用 3 次
- U-Mind: A Unified Framework for Real-Time Multimodal Interaction with Audiovisual Generationxiang deng, Feng Gao, Yong Zhang, Youxin Pang 等CVPR 2026 · 被引用 2 次
- WaveAR: Wavelet-Aware Continuous Autoregressive Diffusion for Accurate Human Motion PredictionShengchuan Gao, Shuo Wang, Yabiao Wang, Ran YiNeurIPS 2025 · 被引用 1 次
- Gaussian-Mixture Latent Flow for Stochastic 3D Human Motion PredictionYue Ma, Frederick W. B. Li, Xiaohui LiangCVPR 2026
它引用的顶会 Paper33
- Denoising Diffusion Probabilistic ModelsJonathan Ho, Ajay Jain, Pieter AbbeelNeurIPS 2020 · 被引用 35,902 次
- High-Resolution Image Synthesis with Latent Diffusion ModelsRobin Rombach, Andreas Blattmann, Dominik Lorenz, Patrick Esser 等CVPR 2022 · 被引用 13,123 次
- Improved Denoising Diffusion Probabilistic ModelsAlexander Quinn Nichol, Prafulla DhariwalICML 2021 · 被引用 5,234 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
- Score-based Generative Modeling in Latent SpaceArash Vahdat, Karsten Kreis, Jan KautzNeurIPS 2021 · 被引用 903 次
相关 Paper
- Human Joint Kinematics Diffusion-Refinement for Stochastic Motion PredictionDong Wei, Huaijiang Sun, Bin Li, Jianfeng Lu 等AAAI 2023 · 被引用 67 次
- KinemaDiff: Towards Diffusion for Coherent and Physically Plausible Human Motion PredictionYe Lu, Jie Wang, Tianyi Liu, Jianjun Gao 等ICLR 2026
- BeLFusion: Latent Diffusion for Behavior-Driven Human Motion PredictionGermán Barquero, Sergio Escalera, Cristina PalmeroICCV 2023 · 被引用 107 次
- Dynamic Future Net: Diversified Human Motion GenerationWenheng Chen, He Wang, Yi Yuan, Tianjia Shao 等ACM MM 2020 · 被引用 20 次
- Consistent View Synthesis with Pose-Guided Diffusion ModelsHung-Yu Tseng, Qinbo Li, Changil Kim, Suhib Alsisan 等CVPR 2023
