Learning to Predict Diverse Human Motions from a Single Image via Mixture Density Networks
원문 초록
Human motion prediction, which plays a key role in computer vision, generally requires a past motion sequence as input. However, in real applications, a complete and correct past motion sequence can be too expensive to achieve. In this paper, we propose a novel approach to predicting future human motions from a much weaker condition, i.e., a single image, with mixture density networks (MDN) modeling. Contrary to most existing deep human motion prediction approaches, the multimodal nature of MDN enables the generation of diverse future motion hypotheses, which well compensates for the strong stochastic ambiguity aggregated by the single input and human motion uncertainty. In designing the loss function, we further introduce the energy-based formulation to flexibly impose prior losses over the learnable parameters of MDN to maintain motion coherence as well as improve the prediction accuracy by customizing the energy functions. Our trained model directly takes an image as input and generates multiple plausible motions that satisfy the given condition. Extensive experiments on two standard benchmark datasets demonstrate the effectiveness of our method in terms of prediction diversity and accuracy.
함께 살펴볼 논문
공통 태그를 근거로 연결했습니다. 실제 인용 관계나 논문의 우수성을 뜻하지 않습니다.
Temporal Continual Learning with Prior Compensation for Human Motion Prediction
Stochastic Human Motion Prediction with Memory of Action Transition and Action Characteristic
M2BeamLLM: Multimodal Sensing-empowered mmWave Beam Prediction with Large Language Models
A Multi-Agent Probabilistic Inference Framework Inspired by Kairanban-Style CoT System with IdoBata Conversation for Debiasing
TrajFlow: Multi-modal Motion Prediction via Flow Matching
Multiscale guidance of AlphaFold3 with heterogeneous cryo-EM data
토론
이 논문과 연결된 포럼 글이 아직 없습니다.