Energy
SANFlow: Semantic-Aware Normalizing Flow for Anomaly Detection and Localization
However, previous NF-based methods forcibly transform the distribution of all features into a single distribution (e.g., unit normal distribution), even when the features can have locally distinct semantic information and thus follow different
Efficient Test-Time Adaptation for Super-Resolution with Second-Order Degradation and Reconstruction Zeshuai Deng 1 Zhuokun Chen
Image super-resolution (SR) aims to learn a mapping from low-resolution (LR) to high-resolution (HR) using paired HR-LR training images.
WildfireSpreadTS: A dataset of multi-modal time series for wildfire spread prediction
We present a multi-temporal, multi-modal remote-sensing dataset for predicting how active wildfires will spread at a resolution of 24 hours. The dataset consists of 13 607 images across 607 fire events in the United States from January 2018 to October 2021. For each fire event, the dataset contains a full time series of daily observations, containing detected active fires and variables related to fuel, topography and weather conditions. The dataset is challenging due to: a) its inputs being multi-temporal, b) the high number of 23 multi-modal input channels, c) highly imbalanced labels and d) noisy labels, due to smoke, clouds, and inaccuracies in the active fire detection.
Transient Neural Radiance Fields for Lidar View Synthesis and 3D Reconstruction Anagh Malik
The ability to sense and reconstruct 3D appearance and geometry is critical to applications in vision, graphics, and beyond.
Dueling Over Dessert, Mastering the Art of Repeated Cake Cutting
We consider two versions: sequential, where Bob observes Alice's cut