Consistency Trajectory Models: Learning Probability Flow ODE Trajectory of Diffusion [PDF]
International Conference on Learning Representations, 2023 Consistency Models (CM) (Song et al., 2023) accelerate score-based diffusion model sampling at the cost of sample quality but lack a natural way to trade-off quality for speed.
Dongjun Kim +8 more
semanticscholar +1 more source
Stochastic Trajectory Prediction via Motion Indeterminacy Diffusion [PDF]
Computer Vision and Pattern Recognition, 2022 Human behavior has the nature of indeterminacy, which requires the pedestrian trajectory prediction system to model the multi-modality of future motion states.
Tianpei Gu +6 more
semanticscholar +1 more source
DragNUWA: Fine-grained Control in Video Generation by Integrating Text, Image, and Trajectory [PDF]
arXiv.org, 2023 Controllable video generation has gained significant attention in recent years. However, two main limitations persist: Firstly, most existing works focus on either text, image, or trajectory-based control, leading to an inability to achieve fine-grained ...
Sheng-Siang Yin +6 more
semanticscholar +1 more source
DenseTNT: End-to-end Trajectory Prediction from Dense Goal Sets [PDF]
IEEE International Conference on Computer Vision, 2021 Due to the stochasticity of human behaviors, predicting the future trajectories of road agents is challenging for autonomous driving. Recently, goal-based multi-trajectory prediction methods are proved to be effective, where they first score over-sampled
Junru Gu, Chen Sun, Hang Zhao
semanticscholar +1 more source
Trajectory-guided Control Prediction for End-to-end Autonomous Driving: A Simple yet Strong Baseline [PDF]
Neural Information Processing Systems, 2022 Current end-to-end autonomous driving methods either run a controller based on a planned trajectory or perform control prediction directly, which have spanned two separately studied lines of research. Seeing their potential mutual benefits to each other,
Peng Wu +5 more
semanticscholar +1 more source
Geometrically Constrained Trajectory Optimization for Multicopters [PDF]
IEEE Transactions on robotics, 2021 In this article, we present an optimization-based framework for multicopter trajectory planning subject to geometrical configuration constraints and user-defined dynamic constraints.
Zhepei Wang +3 more
semanticscholar +1 more source
Social-STGCNN: A Social Spatio-Temporal Graph Convolutional Neural Network for Human Trajectory Prediction [PDF]
Computer Vision and Pattern Recognition, 2020 Better machine understanding of pedestrian behaviors enables faster progress in modeling interactions between agents such as autonomous vehicles and humans.
Abduallah A. Mohamed +3 more
semanticscholar +1 more source
Predicting Dynamic Embedding Trajectory in Temporal Interaction Networks [PDF]
Knowledge Discovery and Data Mining, 2019 Modeling sequential interactions between users and items/products is crucial in domains such as e-commerce, social networking, and education. Representation learning presents an attractive opportunity to model the dynamic evolution of users and items ...
Srijan Kumar, Xikun Zhang, J. Leskovec
semanticscholar +1 more source
SGCN:Sparse Graph Convolution Network for Pedestrian Trajectory Prediction [PDF]
Computer Vision and Pattern Recognition, 2021 Pedestrian trajectory prediction is a key technology in autopilot, which remains to be very challenging due to complex interactions between pedestrians.
Liushuai Shi +6 more
semanticscholar +1 more source
Trace and Pace: Controllable Pedestrian Animation via Guided Trajectory Diffusion [PDF]
Computer Vision and Pattern Recognition, 2023 We introduce a method for generating realistic pedestrian trajectories and full-body animations that can be controlled to meet user-defined goals.
Davis Rempe +7 more
semanticscholar +1 more source