Lidar snowfall simulation for robust 3d object detection

M Hahner, C Sakaridis, M Bijelic… - Proceedings of the …, 2022 - openaccess.thecvf.com
Abstract 3D object detection is a central task for applications such as autonomous driving, in
which the system needs to localize and classify surrounding traffic agents, even in the …

Learning-based real-time imaging through dynamic scattering media

H Liu, F Wang, Y **, X Ma, S Li, Y Bian… - Light: Science & …, 2024 - nature.com
Imaging through dynamic scattering media is one of the most challenging yet fascinating
problems in optics, with applications spanning from biological detection to remote sensing …

Weatherstream: Light transport automation of single image deweathering

H Zhang, Y Ba, E Yang, V Mehra… - Proceedings of the …, 2023 - openaccess.thecvf.com
Today single image deweathering is arguably more sensitive to the dataset type, rather than
the model. We introduce WeatherStream, an automatic pipeline capturing all real-world …

Scatternerf: Seeing through fog with physically-based inverse neural rendering

A Ramazzina, M Bijelic, S Walz… - Proceedings of the …, 2023 - openaccess.thecvf.com
Vision in adverse weather conditions, whether it be snow, rain, or fog is challenging. In these
scenarios, scattering and attenuation severly degrades image quality. Handling such …

Panopticroad: Integrated panoptic road segmentation under adversarial conditions

H Sakaino - Proceedings of the IEEE/CVF Conference on …, 2023 - openaccess.thecvf.com
Segmentation becomes one of the most important methods for scene understanding.
Segmentation plays a central role in recognizing things and stuff in a scene. Among all …

[PDF][PDF] Neural Photo-Finishing.

E Tseng, Y Zhang, L Jebe, X Zhang, Z **a, Y Fan… - ACM Trans …, 2022 - openreview.net
Researchers have proposed several automatic photo-finishing techniques; however, they all
have limitations that prevent widespread adoption. Early machine learning approaches to …

Image-to-image translation for autonomous driving from coarsely-aligned image pairs

Y **a, J Monica, WL Chao, B Hariharan… - … on robotics and …, 2023 - ieeexplore.ieee.org
A self-driving car must be able to reliably handle adverse weather conditions (eg, snowy) to
operate safely. In this paper, we investigate the idea of turning sensor inputs (ie, images) …

Single scattering models for radiative transfer of isotropic and cone-shaped light sources in fog

S Geiger, A Liemert, D Reitzle, M Bijelic… - Optics …, 2022 - opg.optica.org
The simulation of rare edge cases such as adverse weather conditions is the enabler for the
deployment of the next generation of autonomous drones and vehicles into conditions …

MonoWAD: Weather-Adaptive Diffusion Model for Robust Monocular 3D Object Detection

Y Oh, HI Kim, ST Kim, JU Kim - European Conference on Computer Vision, 2024 - Springer
Monocular 3D object detection is an important challenging task in autonomous driving.
Existing methods mainly focus on performing 3D detection in ideal weather conditions …

CMEFusion: Cross-Modal Enhancement and Fusion of FIR and Visible Images

X Tong, X Luo, J Yang, Y Cao - IEEE Transactions on …, 2024 - ieeexplore.ieee.org
The fusion of far infrared (FIR) and visible images aims to generate a high-quality composite
image that contains salient structures and abundant texture details for human visual …