Related papers: SGV3D:Towards Scenario Generalization for Vision-b…
Driving scenes are extremely diverse and complicated that it is impossible to collect all cases with human effort alone. While data augmentation is an effective technique to enrich the training data, existing methods for camera data in…
3D reconstruction and novel view synthesis are critical for validating autonomous driving systems and training advanced perception models. Recent self-supervised methods have gained significant attention due to their cost-effectiveness and…
Human-vehicle cooperative driving has become the critical technology of autonomous driving, which reduces the workload of human drivers. However, the complex and uncertain road environments bring great challenges to the visual perception of…
3D Visual Grounding (3DVG) seeks to locate target objects in 3D scenes using natural language descriptions, enabling downstream applications such as augmented reality and robotics. Existing approaches typically rely on labeled 3D data and…
Deep neural network models have achieved remarkable progress in 3D scene understanding while trained in the closed-set setting and with full labels. However, the major bottleneck is that these models do not have the capacity to recognize…
Self-supervised detection and segmentation of foreground objects aims for accuracy without annotated training data. However, existing approaches predominantly rely on restrictive assumptions on appearance and motion. For scenes with dynamic…
4D radar has received significant attention in autonomous driving thanks to its robustness under adverse weathers. Due to the sparse points and noisy measurements of the 4D radar, most of the research finish the 3D object detection task by…
Visual bird's eye view (BEV) perception, due to its excellent perceptual capabilities, is progressively replacing costly LiDAR-based perception systems, especially in the realm of urban intelligent driving. However, this type of perception…
Dynamic Gaussian splatting has led to impressive scene reconstruction and image synthesis advances in novel views. Existing methods, however, heavily rely on pre-computed poses and Gaussian initialization by Structure from Motion (SfM)…
In autonomous driving, mapping is critical for motion planning but remains an under-utilized resource for perception tasks such as 3D object detection. Maps can provide robust structural priors of the static environment, helping resolve…
The performance of domain adaptation technologies has not yet reached an ideal level in the current 3D object detection field for autonomous driving, which is mainly due to significant differences in the size of vehicles, as well as the…
In this paper, we focus on fully automatic traffic surveillance camera calibration, which we use for speed measurement of passing vehicles. We improve over a recent state-of-the-art camera calibration method for traffic surveillance based…
Single Domain Generalization (SDG) tackles the problem of training a model on a single source domain so that it generalizes to any unseen target domain. While this has been well studied for image classification, the literature on SDG object…
We present VGGT, a feed-forward neural network that directly infers all key 3D attributes of a scene, including camera parameters, point maps, depth maps, and 3D point tracks, from one, a few, or hundreds of its views. This approach is a…
Road surface is the sole contact medium for wheels or robot feet. Reconstructing road surface is crucial for unmanned vehicles and mobile robots. Recent studies on Neural Radiance Fields (NeRF) and Gaussian Splatting (GS) have achieved…
Surround depth estimation provides a cost-effective alternative to LiDAR for 3D perception in autonomous driving. While recent self-supervised methods explore multi-camera settings to improve scale awareness and scene coverage, they are…
We introduce the Visual Implicit Geometry Transformer (ViGT), an autonomous driving geometric model that estimates continuous 3D occupancy fields from surround-view camera rigs. ViGT represents a step towards foundational geometric models…
This paper introduces VisionPAD, a novel self-supervised pre-training paradigm designed for vision-centric algorithms in autonomous driving. In contrast to previous approaches that employ neural rendering with explicit depth supervision,…
Most automated driving systems comprise a diverse sensor set, including several cameras, Radars, and LiDARs, ensuring a complete 360\deg coverage in near and far regions. Unlike Radar and LiDAR, which measure directly in 3D, cameras capture…
Visual sensor networks are used for monitoring traffic in large cities and are promised to support automated driving in complex road segments. The pose of these sensors, i.e. position and orientation, directly determines the coverage of the…