We present AnyBald, a novel framework for realistic hair removal from portrait images captured under diverse in-the-wild conditions. One of the key challenges in this task is the lack of high-quality paired data, as existing datasets are often low-quality, with limited viewpoint variation and diversity, making it difficult to handle real-world cases. To address this, we construct a scalable data augmentation pipeline that synthesizes high-quality hair and non-hair image pairs across diverse real-world scenarios, enabling effective generalization and scalable supervision. With this enriched dataset, we present a new hair removal framework that reformulates pretrained latent diffusion in-painting using learnable text prompts, removing the need for explicit masking at inference. In doing so, our model achieves natural hair removal with semantic preservation via implicit localization. To further enhance spatial precision, we introduce a regularization loss that guides the model to attend specifically to hair regions. Extensive experiments demonstrate that AnyBald outperforms in removing hair while preserving identity and semantics across various in-the-wild domains. Our project page is here: https://vision3d-lab.github.io/anybald/.

Pedestrian behavior prediction is one of the major challenges for intelligent driving systems in urban environments. Pedestrians often exhibit a wide range of behaviors and adequate interpretations of those depend on various sources of information such as pedestrian appearance, states of other road users, the environment layout, etc. To address this problem, we propose a novel multi-modal prediction algorithm that incorporates different sources of information captured from the environment to predict future crossing actions of pedestrians. The proposed model benefits from a hybrid learning architecture consisting of feedforward and recurrent networks for analyzing visual features of the environment and dynamics of the scene. Using the existing 2D pedestrian behavior benchmarks and a 3D driving dataset, we show that our proposed model achieves state-of-the-art performance in pedestrian crossing prediction

Prioritized Experience Replay (ER) has been empirically shown to improve sample efficiency across many domains and attracted great attention; however, there is little theoretical understanding of why such prioritized sampling helps and its limitations. In this work, we take a deep look at the prioritized ER. In a supervised learning setting, we show the equivalence between the error-based prioritized sampling method for minimizing mean squared error and the uniform sampling for cubic power loss. We then provide theoretical insight into why error-based prioritized sampling improves convergence rate upon uniform sampling when minimizing mean squared error during early learning. Based on the insight, we further point out two limitations of the prioritized ER method: 1) outdated priorities and 2) insufficient coverage of the sample space. To mitigate the limitations, we propose our model-based stochastic gradient Langevin dynamics sampling method. We show that our method does provide states distributed close to an ideal prioritized sampling distribution estimated by the brute-force method, which does not suffer from the two limitations. We conduct experiments on both discrete and continuous control problems to show our approach’s efficacy and examine the practical implication of our method in an autonomous driving application.

While supervised learning is widely used for perception modules in conventional autonomous driving solutions, scalability is hindered by the huge amount of data labeling needed. In contrast, while end-to-end architectures do not require labeled data and are potentially more scalable, interpretability is sacrificed. We introduce a novel architecture that is trained in a fully self-supervised fashion for simultaneous multi-step prediction of space-time cost map and road dynamics. Our solution replaces the manually designed cost function for motion planning with a learned high dimensional cost map that is naturally interpretable and allows diverse contextual information to be integrated without manual data labeling. Experiments on real world driving data show that our solution leads to lower number of collisions and road violations in long planning horizons in comparison to baselines, demonstrating the feasibility of fully self-supervised prediction without sacrificing scalability.

In autonomous driving (AD), accurately predicting changes in the environment can effectively improve safety and comfort. Due to complex interactions among traffic participants, however, it is very hard to achieve accurate prediction for a long horizon. To address this challenge, we propose prediction by anticipation, which views interaction in terms of a latent probabilistic generative process wherein some vehicles move partly in response to the anticipated motion of other vehicles. Under this view, consecutive data frames can be factorized into sequential samples from an action-conditional distribution that effectively generalizes to a wider range of actions and driving situations. Our proposed prediction model, variational Bayesian in nature, is trained to maximize the evidence lower bound (ELBO) of the log-likelihood of this conditional distribution. Evaluations of our approach with prominent AD datasets NGSIM I-80 and Argoverse show significant improvement over current state-of-the-art in both accuracy and generalization.

Pedestrian behavior prediction is one of the major challenges for intelligent driving systems. Pedestrians often exhibit complex behaviors influenced by various contextual elements. To address this problem, we propose BiPed, a multitask learning framework that simultaneously predicts trajectories and actions of pedestrians by relying on multi-modal data. Our method benefits from 1) a bifold encoding approach where different data modalities are processed in-dependently allowing them to develop their own representations, and jointly to produce a representation for all modalities using shared parameters; 2) a novel interaction modeling technique that relies on categorical semantic parsing of the scenes to capture interactions between target pedestrians and their surroundings; and 3) a bifold prediction mechanism that uses both independent and shared decoding of multimodal representations. Using public pedestrian behavior benchmark datasets for driving, PIE and JAAD, we highlight the benefits of the proposed method for behavior prediction and show that our model achieves state-of-the-art performance and improves trajectory and action prediction by up to 22% and 9% respectively. We further investigate the contributions of the proposed reasoning techniques via extensive ablation studies.

One of the most crucial yet challenging tasks for autonomous vehicles in urban environments is predicting the future behaviour of nearby pedestrians, especially at points of crossing. Predicting behaviour depends on many social and environmental factors, particularly interactions between road users. Capturing such interactions requires a global view of the scene and dynamics of the road users in three-dimensional space. This information, however, is missing from the current pedestrian behaviour benchmark datasets. Motivated by these challenges, we propose 1) a novel graph-based model for predicting pedestrian crossing action. Our method models pedestrians’ interactions with nearby road users through clustering and relative importance weighting of interactions using features obtained from the bird’s-eye-view. 2) We introduce a new dataset that provides 3D bounding box and pedestrian behavioural annotations for the existing nuScenes dataset. On the new data, our approach achieves state-of-the-art performance by improving on various metrics by more than 15% in comparison to existing methods. The dataset is available at https://github.com/huawei-noah/datasets/PePScenes.

We investigate the multi-step prediction of the drivable space, represented by Occupancy Grid Maps (OGMs), for autonomous vehicles. Our motivation is that accurate multi-step prediction of the drivable space can efficiently improve path planning and navigation resulting in safe, comfortable and optimum paths in autonomous driving. We train a variety of Recurrent Neural Network (RNN) based architectures on the OGM sequences from the KITTI dataset. The results demonstrate significant improvement of the prediction accuracy using our proposed difference learning method, incorporating motion related features, over the state of the art. We remove the egomotion from the OGM sequences by transforming them into a common frame. Although in the transformed sequences the KITTI dataset is heavily biased toward static objects, by learning the difference between consecutive OGMs, our proposed method provides accurate prediction over both the static and moving objects.

In this paper, a novel approach for improving vehicular positioning is presented. This method is based on the cooperation of the vehicles by communicating their measured information about their position. This method consists of two steps. In the first step, we introduce our cooperative map matching method. This map matching method uses the V2V communication in a vehicular ad hoc network (VANET) to exchange global positioning system (GPS) information between vehicles. Having a precise road map, vehicles can apply the road constraints of other vehicles in their own map matching process and acquire a significant improvement in their positioning. After that, we have proposed the concept of a dynamic base station DGPS (DDGPS), which is used by vehicles in the second step to generate and broadcast the GPS pseudorange corrections that can be used by newly arrived vehicles to improve their positioning. The DDGPS is a decentralized cooperative method that aims to improve the GPS positioning by estimating and compensating the common error in GPS pseudorange measurements. It can be seen as an extension of DGPS where the base stations are not necessarily static with an exact known position. In the DDGPS method, the pseudorange corrections are estimated based on the receiver's belief on its positioning and its uncertainty and then broadcasted to other GPS receivers. The performance of the proposed algorithm has been verified with simulations in several realistic scenarios.