Related papers: Learning And-Or Models to Represent Context and Oc…
Estimating and understanding the surroundings of the vehicle precisely forms the basic and crucial step for the autonomous vehicle. The perception system plays a significant role in providing an accurate interpretation of a vehicle's…
In this paper, we present a hierarchical question-answering (QA) approach for scene understanding in autonomous vehicles, balancing cost-efficiency with detailed visual interpretation. The method fine-tunes a compact vision-language model…
Object-centric representation learning aims to decompose visual scenes into fixed-size vectors called "slots" or "object files", where each slot captures a distinct object. Current state-of-the-art object-centric models have shown…
A key challenge for LiDAR-based 3D object detection is to capture sufficient features from large scale 3D scenes especially for distant or/and occluded objects. Albeit recent efforts made by Transformers with the long sequence modeling…
Most existing approaches to autonomous driving fall into one of two categories: modular pipelines, that build an extensive model of the environment, and imitation learning approaches, that map images directly to control outputs. A recently…
AI tasks in the car interior like identifying and localizing externally introduced objects is crucial for response quality of personal assistants. However, computational resources of on-board systems remain highly constrained, restricting…
Occlusion-aware prediction remains a critical challenge in autonomous driving due to the inherent uncertainty of unobserved regions. Existing approaches either overestimate risk based on reachable states or struggle to predict accurate…
Detecting objects in a two-dimensional setting is often insufficient in the context of real-life applications where the surrounding environment needs to be accurately recognized and oriented in three-dimension (3D), such as in the case of…
Understanding driving scenarios is crucial to realizing autonomous driving. Previous works such as map learning and BEV lane detection neglect the connection relationship between lane instances, and traffic elements detection tasks usually…
Object-centric learning (OCL) extracts the representation of objects with slots, offering an exceptional blend of flexibility and interpretability for abstracting low-level perceptual features. A widely adopted method within OCL is slot…
We present an integrated approach for perception and control for an autonomous vehicle and demonstrate this approach in a high-fidelity urban driving simulator. Our approach first builds a model for the environment, then trains a policy…
We present a new learning-based framework to recover vehicle pose in SO(3) from a single RGB image. In contrast to previous works that map from local appearance to observation angles, we explore a progressive approach by extracting…
We present a new open-vocabulary detection approach based on region-centric image-language pretraining to bridge the gap between image-level pretraining and open-vocabulary object detection. At the pretraining phase, we incorporate the…
In this paper, we address the task of detecting semantic parts on partially occluded objects. We consider a scenario where the model is trained using non-occluded images but tested on occluded images. The motivation is that there are…
This paper presents a cost-sensitive active Question-Answering (QA) framework for learning a nine-layer And-Or graph (AOG) from web images. The AOG explicitly represents object categories, poses/viewpoints, parts, and detailed structures…
We propose a novel end-to-end method for cross-view pose estimation. Given a ground-level query image and an aerial image that covers the query's local neighborhood, the 3 Degrees-of-Freedom camera pose of the query is estimated by matching…
Effective Out-of-Distribution (OOD) detection is criti-cal for ensuring the reliability of semantic segmentation models, particularly in complex road environments where safety and accuracy are paramount. Despite recent advancements in large…
Object-centric scene understanding is a fundamental challenge in computer vision. Existing approaches often rely on multi-stage pipelines that first apply pre-trained segmentors to extract individual objects, followed by per-object 3D…
Many existing autonomous driving paradigms involve a multi-stage discrete pipeline of tasks. To better predict the control signals and enhance user safety, an end-to-end approach that benefits from joint spatial-temporal feature learning is…
In this paper, a multi-modal 360$^{\circ}$ framework for 3D object detection and tracking for autonomous vehicles is presented. The process is divided into four main stages. First, images are fed into a CNN network to obtain instance…