MG-GAN: A Multi-Generator Model Preventing Out-of-Distribution Samples in Pedestrian Trajectory Prediction

Dendorfer, Patrick; Elflein, Sven; Leal-Taixé, Laura

doi:10.1109/iccv48922.2021.01291

Cited by 50 publications

(37 citation statements)

References 13 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Facing this challenge, most of prior researches apply the generative model to represent multimodality by a latent variable. For instance, some methods [6,9,12,19,37,43,54] utilize generative adversarial networks (GANs) to spread the distribution over all possible future trajectories, while other methods [3,16,20,25,38,46] exploit conditional variational auto-encoder (CVAE) to encode the multi-modal distribution of future trajectories. Despite the remarkable progress, these methods still face inherent limitations, e.g., training process could be unstable for GANs due to adversarial learning, and CVAE tends to produce unnatural trajectories.…”

Section: … … Determinacy Diversitymentioning

confidence: 99%

“…In addition, the spatialtemporal graph model is applied to jointly model the temporal clues and social interactions [15,16,30,38,44,50]. Beyond social interactions, many methods incorporate the physical environment interactions by introducing the map images [6,19,20,28,37]. Recently, some methods analyze the effect of social interaction and show it is biased [2,27].…”

Section: Related Workmentioning

confidence: 99%

“…Stochastic Prediction Model: Due to the inherent indeterminacy of human behavior, Many stochastic prediction methods are proposed to model the multi-modality of future motions. Some methods [6,9,12,19,37,43,54] employ GANs [11] to model the multi-modality with a noise variable, and another line of methods [3,16,20,25,38,46] apply the CVAE [41] instead. Besides, some methods [7,23,24] propose to learn the grid-based location encoder for multimodal probability prediction.…”

Section: Related Workmentioning

confidence: 99%

“…Here we describe how to calculate the first term D KL . The posterior q(y k−1 |y k , y 0 ) in D KL is tractable and can be represented by Gaussian distribution as: (6) where the closed form of μk (y k , y 0 ) and βk is calculated as:…”

Section: Training Objectivementioning

confidence: 99%

“…Human trajectory prediction plays a crucial role in human-robot interaction systems such as self-driving vehicles and social robots, since human is omnipresent in their environments. Although significant progresses have been achieved over past few years [6,28,29,32,38,45,49,53], predicting the future trajectories of pedestrians remains challenging due to the multi-modality of human motion.…”

Section: Introductionmentioning

confidence: 99%

See 4 more Smart Citations

Stochastic Trajectory Prediction via Motion Indeterminacy Diffusion

Gu¹,

Chen²,

Li³

et al. 2022

Preprint

View full text Add to dashboard Cite

Human behavior has the nature of indeterminacy, which requires the pedestrian trajectory prediction system to model the multi-modality of future motion states. Unlike existing stochastic trajectory prediction methods which usually use a latent variable to represent multi-modality, we explicitly simulate the process of human motion variation from indeterminate to determinate. In this paper, we present a new framework to formulate the trajectory prediction task as a reverse process of motion indeterminacy diffusion (MID), in which we progressively discard indeterminacy from all the walkable areas until reaching the desired trajectory. This process is learned with a parameterized Markov chain conditioned by the observed trajectories. We can adjust the length of the chain to control the degree of indeterminacy and balance the diversity and determinacy of the predictions. Specifically, we encode the history behavior information and the social interactions as a state embedding and devise a Transformer-based diffusion model to capture the temporal dependencies of trajectories. Extensive experiments on the human trajectory prediction benchmarks including the Stanford Drone and ETH/UCY datasets demonstrate the superiority of our method. Code is available at https://github.com/gutianpei/MID.

show abstract