Related papers: GaussianAD: Gaussian-Centric End-to-End Autonomous…

Differentiable rendering techniques have recently shown promising results for free-viewpoint video synthesis of characters. However, such methods, either Gaussian Splatting or neural implicit rendering, typically necessitate per-subject…

Autonomous vehicles are expected to navigate in complex traffic scenarios with multiple surrounding vehicles. The correlations between road users vary over time, the degree of which, in theory, could be infinitely large, thus posing a great…

3D semantic occupancy has rapidly become a research focus in the fields of robotics and autonomous driving environment perception due to its ability to provide more realistic geometric perception and its closer integration with downstream…

A self-driving vehicle must understand its environment to determine the appropriate action. Traditional autonomy systems rely on object detection to find the agents in the scene. However, object detection assumes a discrete set of objects…

Current autonomous driving systems are composed of a perception system and a decision system. Both of them are divided into multiple subsystems built up with lots of human heuristics. An end-to-end approach might clean up the system and…

We present DrivingGaussian++, an efficient and effective framework for realistic reconstructing and controllable editing of surrounding dynamic autonomous driving scenes. DrivingGaussian++ models the static background using incremental 3D…

Modeling the evolutions of driving scenarios is important for the evaluation and decision-making of autonomous driving systems. Most existing methods focus on one aspect of scene evolution such as map generation, motion prediction, and…

In end-to-end autonomous driving,the motion prediction plays a pivotal role in ego-vehicle planning. However, existing methods often rely on globally aggregated motion features, ignoring the fact that planning decisions are primarily…

Self-supervised 3D occupancy prediction offers a promising solution for understanding complex driving scenes without requiring costly 3D annotations. However, training dense occupancy decoders to capture fine-grained geometry and semantics…

Prior works employing pixel-based Gaussian representation have demonstrated efficacy in feed-forward sparse-view reconstruction. However, such representation necessitates cross-view overlap for accurate depth estimation, and is challenged…

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…

Efficient neural representations for dynamic video scenes are critical for applications ranging from video compression to interactive simulations. Yet, existing methods often face challenges related to high memory usage, lengthy training…

Parking is a critical task for autonomous driving systems (ADS), with unique challenges in crowded parking slots and GPS-denied environments. However, existing works focus on 2D parking slot perception, mapping, and localization, 3D…

This paper presents GS-RoadPatching, an inpainting method for driving scene completion by referring to completely reconstructed regions, which are represented by 3D Gaussian Splatting (3DGS). Unlike existing 3DGS inpainting methods that…

In recent years, vision-centric perception has flourished in various autonomous driving tasks, including 3D detection, semantic map construction, motion forecasting, and depth estimation. Nevertheless, the latency of vision-centric…

This paper describes a novel approach to perform vehicle trajectory predictions employing graphic representations. The vehicles are represented using Gaussian distributions into a Bird Eye View. Then the U-net model is used to perform…

Large Language Models (LLMs) and Vision-Language Models (VLMs) have emerged as promising candidates for end-to-end autonomous driving. However, these models typically face challenges in inference latency, action precision, and…

The significance of informative and robust point representations has been widely acknowledged for 3D scene understanding. Despite existing self-supervised pre-training counterparts demonstrating promising performance, the model collapse and…

Modeling and rendering dynamic urban driving scenes is crucial for self-driving simulation. Current high-quality methods typically rely on costly manual object tracklet annotations, while self-supervised approaches fail to capture dynamic…

3D semantic field learning is crucial for applications like autonomous navigation, AR/VR, and robotics, where accurate comprehension of 3D scenes from limited viewpoints is essential. Existing methods struggle under sparse view conditions,…