Related papers: Technical Report for CVPR 2024 WeatherProof Datase…

Deep Learning requires large amounts of data to train models that work well. In data-deficient settings, performance can be degraded. We investigate which Deep Learning methods benefit training models in a data-deficient setting, by…

Removing adverse weather conditions such as rain, raindrop, and snow from images is critical for various real-world applications, including autonomous driving, surveillance, and remote sensing. However, existing multi-task approaches…

Adverse weather severely impairs real-world visual perception, while existing vision models trained on synthetic data with fixed parameters struggle to generalize to complex degradations. To address this, we first construct HFLS-Weather, a…

Semantic segmentation in adverse weather scenarios is a critical task for autonomous driving systems. While foundation models have shown promise, the need for specialized adaptors becomes evident for handling more challenging scenarios. We…

Autonomous driving is rapidly advancing, and Level 2 functions are becoming a standard feature. One of the foremost outstanding hurdles is to obtain robust visual perception in harsh weather and low light conditions where accuracy…

Detecting meaningful events in an untrimmed video is essential for dense video captioning. In this work, we propose a novel and simple model for event sequence generation and explore temporal relationships of the event sequence in the…

Numerical weather prediction has traditionally been based on physical models of the atmosphere. Recently, however, the rise of deep learning has created increased interest in purely data-driven medium-range weather forecasting with first…

This paper deals with the problem of computing surface ice concentration for two different types of ice from digital images of river surface. It presents the results of attempting to solve this problem using several state of the art…

This study describes our system for Task 1 Single-speaker Visual Speech Recognition (VSR) fixed track in the Chinese Continuous Visual Speech Recognition Challenge (CNVSRC) 2023. Specifically, we use intermediate connectionist temporal…

Weakly supervised semantic segmentation is a challenging task as it only takes image-level information as supervision for training but produces pixel-level predictions for testing. To address such a challenging task, most recent…

Weather Recognition plays an important role in our daily lives and many computer vision applications. However, recognizing the weather conditions from a single image remains challenging and has not been studied thoroughly. Generally, most…

In real-world environments, outdoor imaging systems are often affected by disturbances such as rain degradation. Especially, in nighttime driving scenes, insufficient and uneven lighting shrouds the scenes in darkness, resulting degradation…

Image segmentation is considered to be one of the critical tasks in hyperspectral remote sensing image processing. Recently, convolutional neural network (CNN) has established itself as a powerful model in segmentation and classification by…

As 3D perception problems grow in popularity and the need for large-scale labeled datasets for LiDAR semantic segmentation increase, new methods arise that aim to reduce the necessity for dense annotations by employing weakly-supervised…

In the realm of deploying Machine Learning-based Advanced Driver Assistance Systems (ML-ADAS) into real-world scenarios, adverse weather conditions pose a significant challenge. Conventional ML models trained on clear weather data falter…

Numerical weather forecasting using high-resolution physical models often requires extensive computational resources on supercomputers, which diminishes their wide usage in most real-life applications. As a remedy, applying deep learning…

This technical report presents our solution for the CVPR 2026 UG2+ Challenge Track 3: Dynamic Object Segmentation in Turbulence (DOST). We design a training-free multi-signal segmentation pipeline that combines pretrained motion estimation,…

In today's day and age, we face a challenge in detecting deepfake images because of the fast evolution of modern generative models and the poor generalization capability of existing methods. In this paper, we use an ensemble of fine-tuned…

This report provides a detailed description of the method we explored and proposed in the OSR Challenge at the OOD-CV Workshop during ECCV 2024. The challenge required identifying whether a test sample belonged to the semantic classes of a…

State-of-the-art visual localization approaches generally rely on a first image retrieval step whose role is crucial. Yet, retrieval often struggles when facing varying conditions, due to e.g. weather or time of day, with dramatic…