research
∙
09/20/2023
Box2Poly: Memory-Efficient Polygon Prediction of Arbitrarily Shaped and Rotated Text
Recently, Transformer-based text detection techniques have sought to pre...
share
research
∙
09/15/2023
Breathing New Life into 3D Assets with Generative Repainting
Diffusion-based text-to-image models ignited immense attention from the ...
research
∙
09/04/2023
Accuracy and Consistency of Space-based Vegetation Height Maps for Forest Dynamics in Alpine Terrain
Monitoring and understanding forest dynamics is essential for environmen...
research
∙
07/06/2023
Towards accurate instance segmentation in large-scale LiDAR point clouds
Panoptic segmentation is the combination of semantic and instance segmen...
research
∙
06/07/2023
SF-FSDA: Source-Free Few-Shot Domain Adaptive Object Detection with Efficient Labeled Data Factory
Domain adaptive object detection aims to leverage the knowledge learned ...
research
∙
06/01/2023
AGILE3D: Attention Guided Interactive Multi-object 3D Segmentation
During interactive segmentation, a model and a user work together to del...
research
∙
05/24/2023
Mixture of Experts with Uncertainty Voting for Imbalanced Deep Regression Problems
Data imbalance is ubiquitous when applying machine learning to real-worl...
research
∙
05/15/2023
Artificial intelligence to advance Earth observation: a perspective
Earth observation (EO) is a prime instrument for monitoring land and oce...
research
∙
05/02/2023
Neural LiDAR Fields for Novel View Synthesis
We present Neural Fields for LiDAR (NFL), a method to optimise a neural ...
research
∙
04/27/2023
A Review of Panoptic Segmentation for Mobile Mapping Point Clouds
3D point cloud panoptic segmentation is the combined task to (i) assign ...
research
∙
04/05/2023
DEFLOW: Self-supervised 3D Motion Estimation of Debris Flow
Existing work on scene flow estimation focuses on autonomous driving and...
research
∙
12/04/2022
Context-aware multi-head self-attentional neural network model for next location prediction
Accurate activity location prediction is a crucial component of many mob...
research
∙
11/28/2022
Connecting the Dots: Floorplan Reconstruction Using Two-Level Queries
We address 2D floorplan reconstruction from 3D scans. Existing approache...
research
∙
11/23/2022
Tetrahedral Diffusion Models for 3D Shape Generation
Recently, probabilistic denoising diffusion models (DDMs) have greatly a...
research
∙
11/23/2022
BiasBed – Rigorous Texture Bias Evaluation
The well-documented presence of texture bias in modern convolutional neu...
research
∙
11/21/2022
Guided Depth Super-Resolution by Deep Anisotropic Diffusion
Performing super-resolution of a depth image using the guidance from an ...
research
∙
11/08/2022
Fine-grained Population Mapping from Coarse Census Counts and Open Geodata
Fine-grained population maps are needed in several domains, like urban p...
research
∙
09/30/2022
TT-NF: Tensor Train Neural Fields
Learning neural fields has been an active topic in deep learning researc...
research
∙
08/02/2022
T4DT: Tensorizing Time for Learning Temporal 3D Visual Data
Unlike 2D raster images, there is no single dominant representation for ...
research
∙
07/25/2022
Dynamic 3D Scene Analysis by Point Cloud Accumulation
Multi-beam LiDAR sensors, as used on autonomous vehicles and mobile robo...
research
∙
06/22/2022
tntorch: Tensor Network Learning with PyTorch
We present tntorch, a tensor learning framework that supports multiple d...
research
∙
06/13/2022
Satellite-based high-resolution maps of cocoa planted area for Côte d'Ivoire and Ghana
Côte d'Ivoire and Ghana, the world's largest producers of cocoa, account...
research
∙
06/03/2022
Zero-Shot Bird Species Recognition by Learning from Field Guides
We exploit field guides to learn bird species recognition, in particular...
research
∙
04/14/2022
Interactive Object Segmentation in 3D Point Clouds
Deep learning depends on large amounts of labeled training data. Manual ...
research
∙
04/13/2022
A high-resolution canopy height model of the Earth
The worldwide variation in vegetation height is fundamental to the globa...
research
∙
03/29/2022
BARC: Learning to Regress 3D Dog Shape from Images by Exploiting Breed Information
Our goal is to recover the 3D shape and pose of dogs from a single image...
research
∙
03/27/2022
Learning Graph Regularisation for Guided Super-Resolution
We introduce a novel formulation for guided super-resolution. Its core i...
research
∙
11/25/2021
Country-wide Retrieval of Forest Structure From Optical and SAR Satellite Imagery With Bayesian Deep Learning
Monitoring and managing Earth's forests in an informed manner is an impo...
research
∙
08/21/2021
3D Reconstruction from public webcams
In this paper, we investigate the possibility of reconstructing the 3D g...
research
∙
07/29/2021
Mapping Vulnerable Populations with AI
Humanitarian actions require accurate information to efficiently delegat...
research
∙
07/19/2021
Learning a Sensor-invariant Embedding of Satellite Data: A Case Study for Lake Ice Monitoring
Fusing satellite imagery acquired with different sensors has been a long...
research
∙
07/15/2021
High carbon stock mapping at large scale with optical satellite imagery and spaceborne LIDAR
The increasing demand for commodities is leading to changes in land use ...
research
∙
06/07/2021
Digital Taxonomist: Identifying Plant Species in Citizen Scientists' Photographs
Automatic identification of plant specimens from amateur photographs cou...
research
∙
05/29/2021
Cherry-Picking Gradients: Learning Low-Rank Embeddings of Visual Data via Differentiable Cross-Approximation
We propose an end-to-end trainable framework that processes large-scale ...
research
∙
05/24/2021
Mapping oil palm density at country scale: An active learning approach
Accurate mapping of oil palm is important for understanding its past and...
research
∙
03/23/2021
Recent Ice Trends in Swiss Mountain Lakes: 20-year Analysis of MODIS Imagery
Depleting lake ice can serve as an indicator for climate change, just li...
research
∙
03/12/2021
In the light of feature distributions: moment matching for Neural Style Transfer
Style transfer aims to render the content of a given image in the graphi...
research
∙
03/05/2021
Global canopy height estimation with GEDI LIDAR waveforms and Bayesian deep learning
NASA's Global Ecosystem Dynamics Investigation (GEDI) is a key climate m...
research
∙
03/04/2021
PC2WF: 3D Wireframe Reconstruction from Raw Point Clouds
We introduce PC2WF, the first end-to-end trainable deep network architec...
research
∙
02/27/2021
Walk2Map: Extracting Floor Plans from Indoor Walk Trajectories
Recent years have seen a proliferation of new digital products for the e...
research
∙
11/25/2020
PREDATOR: Registration of 3D Point Clouds with Low Overlap
We introduce PREDATOR, a model for pairwise point-cloud registration wit...
research
∙
10/27/2020
Ice Monitoring in Swiss Lakes from Optical Satellites and Webcams using Machine Learning
Continuous observation of climate indicators, such as trends in lake fre...
research
∙
10/15/2020
MOTChallenge: A Benchmark for Single-camera Multiple Target Tracking
Standardized benchmarks have been crucial in pushing the performance of ...
research
∙
08/25/2020
Deep Active Learning in Remote Sensing for data efficient Change Detection
We investigate active learning in the context of deep neural network mod...
research
∙
07/31/2020
KAPLAN: A 3D Point Descriptor for Shape Completion
We present a novel 3D shape completion method that operates directly on ...
research
∙
06/02/2020
From two rolling shutters to one global shutter
Most consumer cameras are equipped with electronic rolling shutter, lead...
research
∙
05/10/2020
Photometric Multi-View Mesh Refinement for High-Resolution Satellite Images
Modern high-resolution satellite sensors collect optical imagery with gr...
research
∙
04/29/2020
Minimal Rolling Shutter Absolute Pose with Unknown Focal Length and Radial Distortion
The internal geometry of most modern consumer cameras is not adequately ...
research
∙
03/20/2020
Privileged Pooling: Supervised attention-based pooling for compensating dataset bias
In this paper we propose a novel supervised image classification method ...
research
∙
03/19/2020