paper-with-me

홈 › Papers

KPNDepth: Depth Estimation of Lane Images under Complex Rainy Environment

2024-05-16 · Zhengxu Shi

Recent advancements in deep neural networks have improved depth estimation in clear, daytime driving scenarios. However, existing methods struggle with rainy conditions due to rain streaks and fog, which distort depth estimation. This paper introduces a novel dual-layer convolutional kernel prediction network for lane depth estimation in rainy environments. It predicts two sets of kernels to mitigate depth loss and rain streak artifacts. To address the scarcity of real rainy lane data, an image synthesis algorithm, RCFLane, is presented, creating a synthetic dataset called RainKITTI. Experiments show the framework's effectiveness in complex rainy conditions.

📄 PDF Abstract BibTeX arXiv:2405.09964

Code (0)

등록된 구현이 없습니다.

Tasks

Depth EstimationImage Generation

Similar Papers 제목 키워드 기반

GGS: Generalizable Gaussian Splatting for Lane Switching in Autonomous Driving

2024-09-04 · Huasong Han, Kaixuan Zhou, Xiaoxiao Long, Yusen Wang 외

We propose GGS, a Generalizable Gaussian Splatting method for Autonomous Driving which can achieve realistic rendering under large viewpoint changes. Previous generalizable 3D gaussian splatting methods are limited to re…

Autonomous DrivingDepth Estimation

MonoGround: Detecting Monocular 3D Objects from the Ground

2022-06-15 · CVPR 2022 1 · Zequn Qin, Xi Li

Monocular 3D object detection has attracted great attention for its advantages in simplicity and cost. Due to the ill-posed 2D to 3D mapping essence from the monocular imaging process, monocular 3D object detection suffe…

3D Object DetectionDepth EstimationMonocular 3D Object DetectionObject+2

Scale Recovery for Monocular Visual Odometry Using Depth Estimated With Deep Convolutional Neural Fields

2017-10-01 · ICCV 2017 10 · Xiaochuan Yin, Xiangwei Wang, Xiaoguo Du, Qijun Chen

Scale recovery is one of the central problems for monocular visual odometry. Normally, road plane and camera height are specified as reference to recover the scale. The performances of these methods depend on the plane r…

Depth EstimationMonocular Visual OdometryVisual Odometry

Plane2Depth: Hierarchical Adaptive Plane Guidance for Monocular Depth Estimation

2024-09-04 · Li Liu, Ruijie Zhu, Jiacheng Deng, Ziyang Song 외

Monocular depth estimation aims to infer a dense depth map from a single image, which is a fundamental and prevalent task in computer vision. Many previous works have shown impressive depth estimation results through car…

Depth EstimationDepth PredictionMonocular Depth Estimation

GeoDepth: From Point-to-Depth to Plane-to-Depth Modeling for Self-Supervised Monocular Depth Estimation

2025-01-01 · CVPR 2025 1 · Haifeng Wu, Shuhang Gu, Lixin Duan, Wen Li

Self-supervised monocular depth estimation has long been treated as a point-wise prediction problem, where the depth of each pixel is usually estimated independently. However, artifacts are often observed in the esti…

Depth EstimationMonocular Depth Estimation