1.4k citations · 4.7k across the 67 of their papers we have counts for
76 papers · 1 filter
MECAIL: Communication-Aware Incremental Learning for Object Detection with 14.6 KB Spatiotemporal Experts
Matthias Neuwirth-Trapp, Maarten Bieshaar, Danda Paudel +3
Intelligent transportation systems require Incremental Learning (IL) to continually improve their overall performance in dynamic environments. However, most edge devices lack the c…
Towards accurate instance segmentation in large-scale LiDAR point clouds
Binbin Xiang, Torben Peters, Theodora Kontogianni +4
Panoptic segmentation is the combination of semantic and instance segmentation: assign the points in a 3D point cloud to semantic categories and partition them into distinct object…
SF-FSDA: Source-Free Few-Shot Domain Adaptive Object Detection with Efficient Labeled Data Factory
Han Sun, Rui Gong, Konrad Schindler +1
Domain adaptive object detection aims to leverage the knowledge learned from a labeled source domain to improve the performance on an unlabeled target domain. Prior works typically…
AGILE3D: Attention Guided Interactive Multi-object 3D Segmentation
Yuanwen Yue, Sabarinath Mahadevan, Jonas Schult +4
During interactive segmentation, a model and a user work together to delineate objects of interest in a 3D point cloud. In an iterative process, the model assigns each data point t…
U-TILISE: A Sequence-to-sequence Model for Cloud Removal in Optical Satellite Time Series
Corinne Stucker, Vivien Sainte Fare Garnot, Konrad Schindler
Satellite image time series in the optical and infrared spectrum suffer from frequent data gaps due to cloud cover, cloud shadows, and temporary sensor outages. It has been a long-…
Neural LiDAR Fields for Novel View Synthesis
Shengyu Huang, Zan Gojcic, Zian Wang +5
We present Neural Fields for LiDAR (NFL), a method to optimise a neural field scene representation from LiDAR measurements, with the goal of synthesizing realistic LiDAR scans from…
DEFLOW: Self-supervised 3D Motion Estimation of Debris Flow
Liyuan Zhu, Yuru Jia, Shengyu Huang +4
Existing work on scene flow estimation focuses on autonomous driving and mobile robotics, while automated solutions are lacking for motion in nature, such as that exhibited by debr…
A Review of Panoptic Segmentation for Mobile Mapping Point Clouds
Binbin Xiang, Yuanwen Yue, Torben Peters +1
3D point cloud panoptic segmentation is the combined task to (i) assign each point to a semantic class and (ii) separate the points in each class into object instances. Recently th…
Connecting the Dots: Floorplan Reconstruction Using Two-Level Queries
Yuanwen Yue, Theodora Kontogianni, Konrad Schindler +1
We address 2D floorplan reconstruction from 3D scans. Existing approaches typically employ heuristically designed multi-stage pipelines. Instead, we formulate floorplan reconstruct…
TetraDiffusion: Tetrahedral Diffusion Models for 3D Shape Generation
Nikolai Kalischek, Torben Peters, Jan D. Wegner +1
Probabilistic denoising diffusion models (DDMs) have set a new standard for 2D image generation. Extending DDMs for 3D content creation is an active field of research. Here, we pro…
BiasBed -- Rigorous Texture Bias Evaluation
Nikolai Kalischek, Rodrigo C. Daudt, Torben Peters +3
The well-documented presence of texture bias in modern convolutional neural networks has led to a plethora of algorithms that promote an emphasis on shape cues, often to support ge…
Guided Depth Super-Resolution by Deep Anisotropic Diffusion
Nando Metzger, Rodrigo Caye Daudt, Konrad Schindler
Performing super-resolution of a depth image using the guidance from an RGB image is a problem that concerns several fields, such as robotics, medical imaging, and remote sensing.…
T4DT: Tensorizing Time for Learning Temporal 3D Visual Data
Mikhail Usvyatsov, Rafael Ballester-Rippoll, Lina Bashaeva +3
Unlike 2D raster images, there is no single dominant representation for 3D visual data processing. Different formats like point clouds, meshes, or implicit functions each have thei…
Dynamic 3D Scene Analysis by Point Cloud Accumulation
Shengyu Huang, Zan Gojcic, Jiahui Huang +2
Multi-beam LiDAR sensors, as used on autonomous vehicles and mobile robots, acquire sequences of 3D range scans ("frames"). Each frame covers the scene sparsely, due to limited ang…
Satellite-based high-resolution maps of cocoa planted area for Côte d'Ivoire and Ghana
Nikolai Kalischek, Nico Lang, Cécile Renier +7
Côte d'Ivoire and Ghana, the world's largest producers of cocoa, account for two thirds of the global cocoa production. In both countries, cocoa is the primary perennial crop, prov…
A high-resolution canopy height model of the Earth
Nico Lang, Walter Jetz, Konrad Schindler +1
The worldwide variation in vegetation height is fundamental to the global carbon cycle and central to the functioning of ecosystems and their biodiversity. Geospatially explicit an…
Interactive Object Segmentation in 3D Point Clouds
Theodora Kontogianni, Ekin Celikkan, Siyu Tang +1
We propose an interactive approach for 3D instance segmentation, where users can iteratively collaborate with a deep learning model to segment objects in a 3D point cloud directly.…
Learning Graph Regularisation for Guided Super-Resolution
Riccardo de Lutio, Alexander Becker, Stefano D'Aronco +3
We introduce a novel formulation for guided super-resolution. Its core is a differentiable optimisation layer that operates on a learned affinity graph. The learned graph potential…
BARC: Learning to Regress 3D Dog Shape from Images by Exploiting Breed Information
Nadine Rueegg, Silvia Zuffi, Konrad Schindler +1
Our goal is to recover the 3D shape and pose of dogs from a single image. This is a challenging task because dogs exhibit a wide range of shapes and appearances, and are highly art…
ImpliCity: City Modeling from Satellite Images with Deep Implicit Occupancy Fields
Corinne Stucker, Bingxin Ke, Yuanwen Yue +3
High-resolution optical satellite sensors, combined with dense stereo algorithms, have made it possible to reconstruct 3D city models from space. However, these models are, in prac…
Country-wide Retrieval of Forest Structure From Optical and SAR Satellite Imagery With Deep Ensembles
Alexander Becker, Stefania Russo, Stefano Puliti +3
Monitoring and managing Earth's forests in an informed manner is an important requirement for addressing challenges like biodiversity loss and climate change. While traditional in…
3D Reconstruction from public webcams
Tianyu Wu, Konrad Schindler, Cenek Albl
We investigate the possibility of 3D scene reconstruction from two or more overlapping webcam streams. A large, and growing, number of webcams observe places of interest and are pu…
Mapping Vulnerable Populations with AI
Benjamin Kellenberger, John E. Vargas-Muñoz, Devis Tuia +6
Humanitarian actions require accurate information to efficiently delegate support operations. Such information can be maps of building footprints, building functions, and populatio…
High carbon stock mapping at large scale with optical satellite imagery and spaceborne LIDAR
Nico Lang, Konrad Schindler, Jan Dirk Wegner
The increasing demand for commodities is leading to changes in land use worldwide. In the tropics, deforestation, which causes high carbon emissions and threatens biodiversity, is…