GazeMotion: Gaze-guided Human Motion Forecasting
원문 초록
We present GazeMotion, a novel method for human motion forecasting that combines information on past human poses with human eye gaze. Inspired by evidence from behavioural sciences showing that human eye and body movements are closely coordinated, GazeMotion first predicts future eye gaze from past gaze, then fuses predicted future gaze and past poses into a gaze-pose graph, and finally uses a residual graph convolutional network to forecast body motion. We extensively evaluate our method on the MoGaze, ADT, and GIMO benchmark datasets and show that it outperforms state-of-the-art methods by up to 7.4% improvement in mean per joint position error. Using head direction as a proxy to gaze, our method still achieves an average improvement of 5.5%. We finally report an online user study showing that our method also outperforms prior methods in terms of perceived realism. These results show the significant information content available in eye gaze for human motion forecasting as well as the effectiveness of our method in exploiting this information.
함께 살펴볼 논문
공통 태그를 근거로 연결했습니다. 실제 인용 관계나 논문의 우수성을 뜻하지 않습니다.
RetroMotion: Retrocausal Motion Forecasting Models are Instructable
M3CAD: Towards Generic Cooperative Autonomous Driving Benchmark
TrajFlow: A Generative Framework for Occupancy Density Estimation Using Normalizing Flows
DeMo: Decoupling Motion Forecasting into Directional Intentions and Dynamic States
Motion Forecasting in Continuous Driving
MDMP: Multi-modal Diffusion for supervised Motion Predictions with uncertainty
토론
이 논문과 연결된 포럼 글이 아직 없습니다.