8 citations · 16 across the 7 of their papers we have counts for
10 papers
Does Image Anonymization Impact Computer Vision Training?
Håkon Hukkelås, Frank Lindseth
Image anonymization is widely adapted in practice to comply with privacy regulations in many regions. However, anonymization often degrades the quality of the data, reducing its ut…
Synthesizing Anyone, Anywhere, in Any Pose
Håkon Hukkelås, Frank Lindseth
We address the task of in-the-wild human figure synthesis, where the primary goal is to synthesize a full body given any region in any image. In-the-wild human figure synthesis has…
FullFormer: Generating Shapes Inside Shapes
Tejaswini Medi, Jawad Tayyub, Muhammad Sarmad +2
Implicit generative models have been widely employed to model 3D data and have recently proven to be successful in encoding and generating high-quality 3D shapes. This work builds…
DeepPrivacy2: Towards Realistic Full-Body Anonymization
Håkon Hukkelås, Frank Lindseth
Generative Adversarial Networks (GANs) are widely adapted for anonymization of human figures. However, current state-of-the-art limit anonymization to the task of face anonymizatio…
Realistic Full-Body Anonymization with Surface-Guided GANs
Håkon Hukkelås, Morten Smebye, Rudolf Mester +1
Recent work on image anonymization has shown that generative adversarial networks (GANs) can generate near-photorealistic faces to anonymize individuals. However, scaling up these…
Teacher-Student Architecture for Mixed Supervised Lung Tumor Segmentation
Vemund Fredriksen, Svein Ole M. Svele, André Pedersen +3
Purpose: Automating tasks such as lung tumor localization and segmentation in radiological images can free valuable time for radiologists and other clinical personnel. Convolutiona…
Image Inpainting with Learnable Feature Imputation
Håkon Hukkelås, Frank Lindseth, Rudolf Mester
A regular convolution layer applying a filter in the same way over known and unknown areas causes visual artifacts in the inpainted image. Several studies address this issue with f…
DeepPrivacy: A Generative Adversarial Network for Face Anonymization
Håkon Hukkelås, Rudolf Mester, Frank Lindseth
We propose a novel architecture which is able to automatically anonymize faces in images while retaining the original data distribution. We ensure total anonymization of all faces…
Multimodal 3D Object Detection from Simulated Pretraining
Åsmund Brekke, Fredrik Vatsendvik, Frank Lindseth
The need for simulated data in autonomous driving applications has become increasingly important, both for validation of pretrained models and for training new models. In order for…
Autonomous Vehicle Control: End-to-end Learning in Simulated Urban Environments
Hege Haavaldsen, Max Aasboe, Frank Lindseth
In recent years, considerable progress has been made towards a vehicle's ability to operate autonomously. An end-to-end approach attempts to achieve autonomous driving using a sing…