paper-with-me

홈 › Papers

Can We Use Diffusion Probabilistic Models for 3D Motion Prediction?

2023-02-28 · Hyemin Ahn, Esteve Valls Mascaro, Dongheui Lee

After many researchers observed fruitfulness from the recent diffusion probabilistic model, its effectiveness in image generation is actively studied these days. In this paper, our objective is to evaluate the potential of diffusion probabilistic models for 3D human motion-related tasks. To this end, this paper presents a study of employing diffusion probabilistic models to predict future 3D human motion(s) from the previously observed motion. Based on the Human 3.6M and HumanEva-I datasets, our results show that diffusion probabilistic models are competitive for both single (deterministic) and multiple (stochastic) 3D motion prediction tasks, after finishing a single training process. In addition, we find out that diffusion probabilistic models can offer an attractive compromise, since they can strike the right balance between the likelihood and diversity of the predicted future motions. Our code is publicly available on the project website: https://sites.google.com/view/diffusion-motion-prediction.

📄 PDF Abstract BibTeX arXiv:2302.14503

Code (0)

등록된 구현이 없습니다.

Tasks

DiversityImage Generationmotion prediction

Methods 이 논문이 사용한 방법론

Diffusion Diffusion models generate samples by gradually removing noise from a signal, and their training objective can be expressed as a reweighted variational lower-bound…

Similar Papers 제목 키워드 기반

DiffMOT: A Real-time Diffusion-based Multiple Object Tracker with Non-linear Prediction

2024-03-04 · CVPR 2024 1 · Weiyi Lv, Yuhang Huang, Ning Zhang, Ruei-Sung Lin 외

In Multiple Object Tracking, objects often exhibit non-linear motion of acceleration and deceleration, with irregular direction changes. Tacking-by-detection (TBD) trackers with Kalman Filter motion prediction work well …

motion predictionMultiple Object TrackingObject Tracking

Human Joint Kinematics Diffusion-Refinement for Stochastic Motion Prediction

2022-10-12 · Dong Wei, Huaijiang Sun, Bin Li, Jianfeng Lu 외

Stochastic human motion prediction aims to forecast multiple plausible future motions given a single pose sequence from the past. Most previous works focus on designing elaborate losses to improve the accuracy, while the…

DecoderDiversityHuman motion predictionmotion prediction+2

Nonisotropic Gaussian Diffusion for Realistic 3D Human Motion Prediction

2025-01-10 · CVPR 2025 1 · Cecilia Curreli, Dominik Muhle, Abhishek Saroha, Zhenzhang Ye 외

Probabilistic human motion prediction aims to forecast multiple possible future movements from past observations. While current approaches report high diversity and realism, they often generate motions with undetected li…

DiversityHuman motion predictionInductive Biasmotion prediction

SMamDiff: Spatial Mamba for Stochastic Human Motion Prediction

2025-11-29 · Junqiao Fan, Pengfei Liu, Haocong Rao arxiv

With intelligent room-side sensing and service robots widely deployed, human motion prediction (HMP) is essential for safe, proactive assistance. However, many existing HMP methods either produce a single, deterministic …

Modiff: Action-Conditioned 3D Motion Generation with Denoising Diffusion Probabilistic Models

2023-01-10 · Mengyi Zhao, Mengyuan Liu, Bin Ren, Shuling Dai 외

Diffusion-based generative models have recently emerged as powerful solutions for high-quality synthesis in multiple domains. Leveraging the bidirectional Markov chains, diffusion probabilistic models generate samples by…

DenoisingMotion Generation