Related papers: MADrive: Memory-Augmented Driving Scene Modeling

This paper proposes a photorealistic real-time dense 3D mapping system that utilizes a learning-based image enhancement method and mesh-based map representation. Due to the characteristics of the underwater environment, where problems such…

In this paper, we rethink the problem of scene reconstruction from an embodied agent's perspective: While the classic view focuses on the reconstruction accuracy, our new perspective emphasizes the underlying functions and constraints such…

Autonomous Vehicles (AVs) need an accurate and up-to-date representation of the environment for safe navigation. Traditional methods, which often rely on detailed environmental representations constructed offline, struggle in dynamically…

Novel view synthesis of urban scenes is essential for autonomous driving-related applications.Existing NeRF and 3DGS-based methods show promising results in achieving photorealistic renderings but require slow, per-scene optimization. We…

Simulation plays a crucial role in the development of autonomous vehicles (AVs) due to the potential risks associated with real-world testing. Although significant progress has been made in the visual aspects of simulators, generating…

Rendering realistic images from 3D reconstruction is an essential task of many Computer Vision and Robotics pipelines, notably for mixed-reality applications as well as training autonomous agents in simulated environments. However, the…

Place recognition is a crucial component that enables autonomous vehicles to obtain localization results in GPS-denied environments. In recent years, multimodal place recognition methods have gained increasing attention. They overcome the…

Large-scale datasets have fueled recent advancements in AI-based autonomous vehicle research. However, these datasets are usually collected from a single vehicle's one-time pass of a certain location, lacking multiagent interactions or…

Urban scene reconstruction is critical for autonomous driving, enabling structured 3D representations for data synthesis and closed-loop testing. Supervised approaches rely on costly human annotations and lack scalability, while current…

The well-established modular autonomous driving system is decoupled into different standalone tasks, e.g. perception, prediction and planning, suffering from information loss and error accumulation across modules. In contrast, end-to-end…

Current 3D reconstruction techniques struggle to infer unbounded scenes from a few images faithfully. Specifically, existing methods have high computational demands, require detailed pose information, and cannot reconstruct occluded regions…

Vision-Language-Action (VLA) models have emerged as a promising paradigm for end-to-end autonomous driving, yet their reliance on implicit parametric knowledge limits generalization in long-tail scenarios. While Retrieval-Augmented…

In recent years, vision-based end-to-end autonomous driving has emerged as a new paradigm. However, popular end-to-end approaches typically rely on visual feature extraction networks trained under label supervision. This limited supervision…

Prior point cloud provides 3D environmental context, which enhances the capabilities of monocular camera in downstream vision tasks, such as 3D object detection, via data fusion. However, the absence of accurate and automated registration…

As autonomous driving technology progresses, the need for precise trajectory prediction models becomes paramount. This paper introduces an innovative model that infuses cognitive insights into trajectory prediction, focusing on perceived…

Recent advancements in 4D scene reconstruction, particularly those leveraging diffusion priors, have shown promise for novel view synthesis in autonomous driving. However, these methods often process frames independently or in a…

In this paper, we introduce Semi-SMD, a novel metric depth estimation framework tailored for surrounding cameras equipment in autonomous driving. In this work, the input data consists of adjacent surrounding frames and camera parameters. We…

Accurate and high-fidelity driving scene reconstruction demands the effective utilization of comprehensive scene information as conditional inputs. Existing methods predominantly rely on 3D bounding boxes and BEV road maps for foreground…

Ensuring the safety of Autonomous Driving Systems (ADS) requires realistic and reproducible test scenarios, yet extracting such scenarios from multimodal crash reports remains a major challenge. Large Language Models (LLMs) often…

Monocular Metric Depth Estimation (MMDE) is essential for physically intelligent systems, yet accurate depth estimation for underrepresented classes in complex scenes remains a persistent challenge. To address this, we propose RAD, a…