Hugging Face Trending Papers

Guided Super-Resolution of Digital Elevation Models with Diffusion-Based Image Generators

The paper presents a method for enhancing coarse 5 m digital surface models (DSMs) to 0.5 m resolution by guiding a denoising diffusion process with high‑resolution spectral images. This approach transfers fine visual details—such as crisp outlines and roof structures—from the imagery into the elevation maps, yielding more accurate surface geometry than traditional interpolation or filtering. Experiments on Central European cities show that the resulting DSMs exhibit improved structural detail and overall quality.

arXiv Computer Vision
Sep 11

Guided Super-Resolution of Digital Elevation Models with Diffusion-Based Image Generators

The paper proposes a method to enhance coarse 5 m digital surface models (DSMs) to 0.5 m resolution by guiding the super‑resolution process with high‑resolution spectral images. It uses denoising diffusion to transfer image‑visible details, such as crisp outlines and roof structures, into the elevation maps, achieving more accurate surface geometry than traditional interpolation or filtering. Experiments on Central European cities show that the approach yields high‑quality DSMs with improved structural detail.

By Armand Mihai Nicolicioiu, Dominik Narnhofer, Nando Metzger, Daniel Panangian, Ksenia Bittner, Konrad Schindler
arXiv Computer Vision
Sep 4

Skyfall-GS: Synthesizing Immersive 3D Urban Scenes from Satellite Imagery

Skyfall-GS is a hybrid framework that generates large‑scale, city‑block‑sized 3D urban scenes by combining satellite imagery for coarse geometry with open‑domain diffusion models for detailed appearance. It uses a curriculum‑driven iterative refinement to improve geometric completeness and photorealistic textures, eliminating the need for costly 3D annotations. Experiments show that Skyfall‑GS achieves better cross‑view geometry consistency and more realistic textures than existing methods.

By Jie-Ying Lee, Yi-Ruei Liu, Shr-Ruei Tsai, Wei-Cheng Chang, Chung-Ho Wu, Jiewen Chan, Zhenjun Zhao, Chieh Hubert Lin, Yu-Lun Liu
arXiv Machine Learning
Aug 21

Evaluating Neural Cartographic Relief Shading for Urban Environments: A Downtown Calgary Study Using High-Resolution DEM and DSM Data

arXiv:2608. 20149v1 Announce Type: new Abstract: This article explores the performance of analytical and neural-based hillshading methods in a dense urban environment using high-resolution digital elevation model (DEM) and digital surface model (DSM) data for downtown Calgary.

By Emmanuel Stefanakis
arXiv Computer Vision
Aug 27

Uncertainty-Guided Latent Diffusion Models for Faithful Super Resolution

UGDiff introduces an uncertainty-guided diffusion paradigm for single-image super-resolution, aiming to improve the perception‑distortion trade‑off. The method estimates reconstruction uncertainty of latent features from a high‑fidelity image and uses this uncertainty, along with diffusion sampler posterior variance, to selectively restore high‑frequency details in uncertain regions while preserving fidelity elsewhere. Experiments show that UGDiff outperforms state‑of‑the‑art diffusion‑based SR methods.

By Ren Wang, Yung-Yu Chuang
Hugging Face Trending Papers
Aug 17

Remote-Sensing City Layout Extraction with MLLM

Remote-sensing systems usually describe urban content with detection boxes, semantic masks, or vector boundaries. Such outputs locate classes and support image-plane scoring, yet they do not by themselves constitute an executable layout that retains object identities, typed relations, topology, and regeneration rules.