prs-eth

[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 2025] RollingDepth: Video Depth without Video Models

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

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

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

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

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

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

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

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

[IROS 2020] Indoor Scene Recognition in 3D

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

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