Photogrammetry and Remote Sensing Lab ORG

[CVPR 2024 - Oral, Best Paper Award Candidate] Marigold: Repurposing Diffusion-Based Image Generators for Monocular Depth Estimation

[TMLR 2025] Thera: Aliasing-Free Arbitrary-Scale Super-Resolution with Neural Heat Fields

[CVPR 2021, Oral] PREDATOR: Registration of 3D Point Clouds with Low Overlap.

[CVPR 2026 Highlight] LitePT: Lighter Yet Stronger Point Transformer

[CVPR 2025] RollingDepth: Video Depth without Video Models

[ICCV 2025] Zero-Shot Monocular Depth Completion with Guided Diffusion

Code for "Point2CAD: Reverse Engineering CAD Models from 3D Point Clouds"

PaGeR — Unified Panoramic Geometry Estimation via Multi-View Foundation Models

[ECCV 2022] Dynamic 3D Scene Analysis by Point Cloud Accumulation

[CVPR 2023] Guided Depth Super-Resolution by Deep Anisotropic Diffusion

official source code for paper entitled "Automated forest inventory: analysis of high-density airborne LiDAR point clouds with 3D deep learning"

Code and dataset of paper "TOWARDS ACCURATE INSTANCE SEGMENTATION IN LARGE-SCALE LIDAR POINT CLOUDS"

[ISPRS Journal of Photogrammetry and Remote Sensing, 2022] ResDepth: A Deep Residual Prior For 3D Reconstruction From High-resolution Satellite Images

[CVPR 2024, highlight] Dynamic LiDAR Re-simulation using Compositional Neural Fields

[ECCV 2024] DGInStyle: Domain-Generalizable Semantic Segmentation with Image Diffusion Models and Stylized Semantic Control

[ICCV 2019] Guided Super-Resolution as a Learned Pixel-to-Pixel Transformation

The implementation of our paper "Point2Building: Reconstructing Buildings from Airborne LiDAR Point Clouds"

No description.

No description.

[ISPRS Congress 2022, Best Young Author Award] ImpliCity: City Modeling from Satellite Images with Deep Implicit Occupancy Fields

[CVPR 2022] Learning Graph Regularisation for Guided Super-Resolution

[IROS 2020] Indoor Scene Recognition in 3D

LoRA-Ensemble: Efficient Uncertainty Modelling for Self-attention Networks

No description.

An Open-Source Tool for Mapping War Destruction at Scale in Ukraine using Sentinel-1 Time Series

[RSE 2024] 🍿POPCORN: High-resolution Population Maps Derived from Sentinel-1 and Sentinel-2 🌍🛰️

[ISPRS Congress 2020] Lake Ice Detection from Sentinel-1 SAR with Deep Learning (Deeplabv3+, Tensorflow). The data was collected from Google Earth Engine platform.

[CVPRW 2023, Best Paper Award] DeFlow: Self-supervised 3D Motion Estimation of Debris Flow

[NeurIPS 2022] FiLM-Ensemble: Probabilistic Deep Learning via Feature-wise Linear Modulation

Official code for "Stitched Value Model for Diffusion Alignment"

Downstream semantic segmentation evaluation of DGInStyle.

[TGRS21] Crop Classification under Varying Cloud Cover with Neural Ordinary Differential Equations

[ICLR 2026] Continuous Space-Time Video Super-Resolution with 3D Fourier Fields

Source code for paper entitled "A Review of Panoptic Segmentation for Mobile Mapping Point Clouds"

xBD-S12: Building damage assessment from Copernicus Sentinel-1 and Sentinel-2 satellite imagery.

No description.

[MDPI Remote Sensing 2020] Lake Detection and Lake Ice Monitoring with Webcams and Crowd-​Sourced Images (RGB) using Deep Learning (Deeplabv3+, Tensorflow)

No description.

[ICCV2021] Code for the paper "Cherry-Picking Gradients: Learning Low-Rank Embeddings of Visual Data via Differentiable Cross-Approximation"

[BMVC2022] Code for paper "Tensorizing 4D Visual Data Along Temporal Dimension"

RGB dataset (images from webcams monitoring the two Swiss lakes St. Moritz and Sihl)

The unrealized potential of agroforestry for an emissions-intensive agricultural commodity

[RSE21] Pytorch code for hierarchical time series classification with multi-stage convolutional RNN

Bildverarbeitung FS2023 at ETH Zurich

[ISPRS Annals 2018] Lake Ice Monitoring with Webcam Images (RGB) using Deep Learning (FC-DenseNet, Keras)