相关论文: Robo3D: Towards Robust and Reliable 3D Perception …

Depth estimation from monocular images is pivotal for real-world visual perception systems. While current learning-based depth estimation models train and test on meticulously curated data, they often overlook out-of-distribution (OoD)…

3D object detection is an important task in autonomous driving to perceive the surroundings. Despite the excellent performance, the existing 3D detectors lack the robustness to real-world corruptions caused by adverse weathers, sensor…

The recent advances in camera-based bird's eye view (BEV) representation exhibit great potential for in-vehicle 3D perception. Despite the substantial progress achieved on standard benchmarks, the robustness of BEV algorithms has not been…

The performance of computer vision models are susceptible to unexpected changes in input images caused by sensor errors or extreme imaging environments, known as common corruptions (e.g. noise, blur, illumination changes). These corruptions…

3D perception, especially point cloud classification, has achieved substantial progress. However, in real-world deployment, point cloud corruptions are inevitable due to the scene complexity, sensor inaccuracy, and processing imprecision.…

Driving systems often rely on high-definition (HD) maps for precise environmental information, which is crucial for planning and navigation. While current HD map constructors perform well under ideal conditions, their resilience to…

Deep neural networks on 3D point cloud data have been widely used in the real world, especially in safety-critical applications. However, their robustness against corruptions is less studied. In this paper, we present ModelNet40-C, the…

In the realm of modern autonomous driving, the perception system is indispensable for accurately assessing the state of the surrounding environment, thereby enabling informed prediction and planning. The key step to this system is related…

We introduce a set of image transformations that can be used as corruptions to evaluate the robustness of models as well as data augmentation mechanisms for training neural networks. The primary distinction of the proposed transformations…

Standard benchmarks for optical flow, scene flow, and stereo vision algorithms generally focus on model accuracy rather than robustness to image corruptions like noise or rain. Hence, the resilience of models to such real-world…

Multi-sensor fusion models play a crucial role in autonomous driving perception, particularly in tasks like 3D object detection and HD map construction. These models provide essential and comprehensive static environmental information for…

In recent years, significant progress has been achieved for 3D object detection on point clouds thanks to the advances in 3D data collection and deep learning techniques. Nevertheless, 3D scenes exhibit a lot of variations and are prone to…

Multi-modal 3D object detection models for automated driving have demonstrated exceptional performance on computer vision benchmarks like nuScenes. However, their reliance on densely sampled LiDAR point clouds and meticulously calibrated…

Object detection through LiDAR-based point cloud has recently been important in autonomous driving. Although achieving high accuracy on public benchmarks, the state-of-the-art detectors may still go wrong and cause a heavy loss due to the…

Synthetic corruptions gathered into a benchmark are frequently used to measure neural network robustness to distribution shifts. However, robustness to synthetic corruption benchmarks is not always predictive of robustness to distribution…

Recent advancements in bird's eye view (BEV) representations have shown remarkable promise for in-vehicle 3D perception. However, while these methods have achieved impressive results on standard benchmarks, their robustness in varied…

The outstanding performance of Large Multimodal Models (LMMs) has made them widely applied in vision-related tasks. However, various corruptions in the real world mean that images will not be as ideal as in simulations, presenting…

The robustness of object detection models is a major concern when applied to real-world scenarios. The performance of most models tends to degrade when confronted with images affected by corruptions, since they are usually trained and…

Pose estimation aims to accurately identify anatomical keypoints in humans and animals using monocular images, which is crucial for various applications such as human-machine interaction, embodied AI, and autonomous driving. While current…

Earth observation foundation models have shown strong generalization across multiple Earth observation tasks, but their robustness under real-world perturbations remains underexplored. To bridge this gap, we introduce REOBench, the first…