paper-with-me

홈 › Papers

Fully reversible neural networks for large-scale surface and sub-surface characterization via remote sensing

2020-03-16 · Bas Peters, Eldad Haber, Keegan Lensink

The large spatial/frequency scale of hyperspectral and airborne magnetic and gravitational data causes memory issues when using convolutional neural networks for (sub-) surface characterization. Recently developed fully reversible networks can mostly avoid memory limitations by virtue of having a low and fixed memory requirement for storing network states, as opposed to the typical linear memory growth with depth. Fully reversible networks enable the training of deep neural networks that take in entire data volumes, and create semantic segmentations in one go. This approach avoids the need to work in small patches or map a data patch to the class of just the central pixel. The cross-entropy loss function requires small modifications to work in conjunction with a fully reversible network and learn from sparsely sampled labels without ever seeing fully labeled ground truth. We show examples from land-use change detection from hyperspectral time-lapse data, and regional aquifer mapping from airborne geophysical and geological data.

📄 PDF Abstract BibTeX arXiv:2003.07474

Code (0)

등록된 구현이 없습니다.

Tasks

Change Detection

Similar Papers 제목 키워드 기반

Fully invertible hyperbolic neural networks for segmenting large-scale surface and sub-surface data

2024-06-30 · Bas Peters, Eldad Haber, Keegan Lensink

The large spatial/temporal/frequency scale of geoscience and remote-sensing datasets causes memory issues when using convolutional neural networks for (sub-) surface data segmentation. Recently developed fully reversible…

Dimensionality ReductionSeismic Imaging

Complete virtual unwrapping and reading of a rolled Herculaneum papyrus

2026-06-27 · Giorgio Angelotti, Stephen Parsons, Federica Nicolardi, Youssef Nader 외 arxiv

The carbonized papyri from Herculaneum preserve the only large-scale library to survive from classical antiquity, but many unopened rolls remain unread because physical opening risks irreversible damage. X-ray computed m…

SurfaceNet: An End-to-end 3D Neural Network for Multiview Stereopsis

2017-08-05 · ICCV 2017 10 · Mengqi Ji, Juergen Gall, Haitian Zheng, Yebin Liu 외

This paper proposes an end-to-end learning framework for multiview stereopsis. We term the network SurfaceNet. It takes a set of images and their corresponding camera parameters as input and directly infers the 3D model.…

City-Level 3D Surface Reconstruction with Viewpoint Orientation Partitioning and Scene Completion

2026-07-04 · Liang Han, Wenyuan Zhang, Junsheng Zhou, Yu-Shen Liu 외 arxiv

Multi-view 3D surface reconstruction is a longstanding challenge in computer vision. Although recent large-scale reconstruction methods based on 3D Gaussian Splatting (3DGS) achieve impressive novel-view synthesis, produ…

Signal-Aware Conditional Diffusion Surrogates for Transonic Wing Pressure Prediction

2026-04-13 · Víctor Francés-Belda, Carlos Sanmiguel Vila, Rodrigo Castellanos arxiv

Accurate and efficient surrogate models for aerodynamic surface pressure fields are essential for accelerating aircraft design and analysis, yet deterministic regressors trained with pointwise losses often smooth sharp n…