GBD-TS: Goal-based Pedestrian Trajectory Prediction with Diffusion using
Tree Sampling Algorithm
- URL: http://arxiv.org/abs/2311.14922v1
- Date: Sat, 25 Nov 2023 03:55:06 GMT
- Title: GBD-TS: Goal-based Pedestrian Trajectory Prediction with Diffusion using
Tree Sampling Algorithm
- Authors: Ge Sun, Sheng Wang, Yang Xiao, Lei Zhu, Ming Liu
- Abstract summary: We propose a novel scene-aware multi-modal pedestrian trajectory prediction framework called GBD.
First, the goal predictor produces multiple goals, and then the diffusion network generates multi-modal trajectories conditioned on these goals.
- Score: 18.367711156885203
- License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
- Abstract: Predicting pedestrian trajectories is crucial for improving the safety and
effectiveness of autonomous driving and mobile robots. However, this task is
nontrivial due to the inherent stochasticity of human motion, which naturally
requires the predictor to generate multi-model prediction. Previous works have
used various generative methods, such as GAN and VAE, for pedestrian trajectory
prediction. Nevertheless, these methods may suffer from problems, including
mode collapse and relatively low-quality results. The denoising diffusion
probabilistic model (DDPM) has recently been applied to trajectory prediction
due to its simple training process and powerful reconstruction ability.
However, current diffusion-based methods are straightforward without fully
leveraging input information and usually require many denoising iterations
leading to a long inference time or an additional network for initialization.
To address these challenges and promote the application of diffusion models in
trajectory prediction, we propose a novel scene-aware multi-modal pedestrian
trajectory prediction framework called GBD. GBD combines goal prediction with
the diffusion network. First, the goal predictor produces multiple goals, and
then the diffusion network generates multi-modal trajectories conditioned on
these goals. Furthermore, we introduce a new diffusion sampling algorithm named
tree sampling (TS), which leverages common feature to reduce the inference time
and improve accuracy for multi-modal prediction. Experimental results
demonstrate that our GBD-TS method achieves state-of-the-art performance with
real-time inference speed.
Related papers
- Diffusion Forcing: Next-token Prediction Meets Full-Sequence Diffusion [61.03681839276652]
Diffusion Forcing is a new training paradigm where a diffusion model is trained to denoise a set of tokens with independent per-token noise levels.
We apply Diffusion Forcing to sequence generative modeling by training a causal next-token prediction model to generate one or several future tokens.
arXiv Detail & Related papers (2024-07-01T15:43:25Z) - A Multi-Stage Goal-Driven Network for Pedestrian Trajectory Prediction [6.137256382926171]
This paper proposes a novel method for pedestrian trajectory prediction, called multi-stage goal-driven network (MGNet)
The network comprises three main components: a conditional variational autoencoder (CVAE), an attention module, and a multi-stage goal evaluator.
The effectiveness of MGNet is demonstrated through comprehensive experiments on the JAAD and PIE datasets.
arXiv Detail & Related papers (2024-06-26T03:59:21Z) - ADM: Accelerated Diffusion Model via Estimated Priors for Robust Motion Prediction under Uncertainties [6.865435680843742]
We propose a novel diffusion-based, acceleratable framework that adeptly predicts future trajectories of agents with enhanced resistance to noise.
Our method meets the rigorous real-time operational standards essential for autonomous vehicles.
It achieves significant improvement in multi-agent motion prediction on the Argoverse 1 motion forecasting dataset.
arXiv Detail & Related papers (2024-05-01T18:16:55Z) - Exploiting Diffusion Prior for Generalizable Dense Prediction [85.4563592053464]
Recent advanced Text-to-Image (T2I) diffusion models are sometimes too imaginative for existing off-the-shelf dense predictors to estimate.
We introduce DMP, a pipeline utilizing pre-trained T2I models as a prior for dense prediction tasks.
Despite limited-domain training data, the approach yields faithful estimations for arbitrary images, surpassing existing state-of-the-art algorithms.
arXiv Detail & Related papers (2023-11-30T18:59:44Z) - DICE: Diverse Diffusion Model with Scoring for Trajectory Prediction [7.346307332191997]
We present a novel framework that leverages diffusion models for predicting future trajectories in a computationally efficient manner.
We employ an efficient sampling mechanism that allows us to maximize the number of sampled trajectories for improved accuracy.
We show the effectiveness of our approach by conducting empirical evaluations on common pedestrian (UCY/ETH) and autonomous driving (nuScenes) benchmark datasets.
arXiv Detail & Related papers (2023-10-23T05:04:23Z) - CamoDiffusion: Camouflaged Object Detection via Conditional Diffusion
Models [72.93652777646233]
Camouflaged Object Detection (COD) is a challenging task in computer vision due to the high similarity between camouflaged objects and their surroundings.
We propose a new paradigm that treats COD as a conditional mask-generation task leveraging diffusion models.
Our method, dubbed CamoDiffusion, employs the denoising process of diffusion models to iteratively reduce the noise of the mask.
arXiv Detail & Related papers (2023-05-29T07:49:44Z) - Leapfrog Diffusion Model for Stochastic Trajectory Prediction [32.36667797656046]
We present LEapfrog Diffusion model (LED), a novel diffusion-based trajectory prediction model.
LED provides real-time, precise, and diverse predictions.
LED consistently improves performance and achieves 23.7%/21.9% ADE/FDE improvement on NFL.
arXiv Detail & Related papers (2023-03-20T06:32:48Z) - Generative Time Series Forecasting with Diffusion, Denoise, and
Disentanglement [51.55157852647306]
Time series forecasting has been a widely explored task of great importance in many applications.
It is common that real-world time series data are recorded in a short time period, which results in a big gap between the deep model and the limited and noisy time series.
We propose to address the time series forecasting problem with generative modeling and propose a bidirectional variational auto-encoder equipped with diffusion, denoise, and disentanglement.
arXiv Detail & Related papers (2023-01-08T12:20:46Z) - Interpretable Social Anchors for Human Trajectory Forecasting in Crowds [84.20437268671733]
We propose a neural network-based system to predict human trajectory in crowds.
We learn interpretable rule-based intents, and then utilise the expressibility of neural networks to model scene-specific residual.
Our architecture is tested on the interaction-centric benchmark TrajNet++.
arXiv Detail & Related papers (2021-05-07T09:22:34Z) - Adversarial Refinement Network for Human Motion Prediction [61.50462663314644]
Two popular methods, recurrent neural networks and feed-forward deep networks, are able to predict rough motion trend.
We propose an Adversarial Refinement Network (ARNet) following a simple yet effective coarse-to-fine mechanism with novel adversarial error augmentation.
arXiv Detail & Related papers (2020-11-23T05:42:20Z)
This list is automatically generated from the titles and abstracts of the papers in this site.
This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.