output
20022026
most citedMethods for Interpreting and Understanding Deep Neural Networks

2.8k citations

Showing 2025 · cs.CVShow all

11 papers · 2 filters

cs.CV2025★ 7 cited

Seabed-Net: A multi-task network for joint bathymetry estimation and seabed classification from remote sensing imagery in shallow waters

Panagiotis Agrafiotis, Begüm Demir

Accurate, detailed, and regularly updated bathymetry, coupled with complex semantic content, is essential for under-mapped shallow-water environments facing increasing climatologic…

cs.CV2025

Geometry-Aware Video Inpainting for Joint Headset Occlusion Removal and Face Reconstruction in Social XR

Fatemeh Ghorbani Lohesara, Karen Eguiazarian, Sebastian Knorr

Head-mounted displays (HMDs) are essential for experiencing extended reality (XR) environments and observing virtual content. However, they obscure the upper part of the user's fac…

cs.CV2025★ 1 cited

Enhancing 3D point accuracy of laser scanner through multi-stage convolutional neural network for applications in construction

Qinyuan Fan, Clemens Gühmann

We propose a multi-stage convolutional neural network (MSCNN) based integrated method for reducing uncertainty of 3D point accuracy of lasar scanner (LS) in rough indoor rooms, pro…

cs.CV2025

Physical Annotation for Automated Optical Inspection: A Concept for In-Situ, Pointer-Based Training Data Generation

Oliver Krumpek, Oliver Heimann, Jörg Krüger

This paper introduces a novel physical annotation system designed to generate training data for automated optical inspection. The system uses pointer-based in-situ interaction to t…

cs.CV2025★ 3 cited

Adjustable Spatio-Spectral Hyperspectral Image Compression Network

Martin Hermann Paul Fuchs, Behnood Rasti, Begüm Demir

With the rapid growth of hyperspectral data archives in remote sensing (RS), the need for efficient storage has become essential, driving significant attention toward learning-base…

cs.CV2025

Continual Self-Supervised Learning with Masked Autoencoders in Remote Sensing

Lars Möllenbrok, Behnood Rasti, Begüm Demir

The development of continual learning (CL) methods, which aim to learn new tasks in a sequential manner from the training data acquired continuously, has gained great attention in…