paper-with-me

홈 › Papers

DeepSim: Semantic similarity metrics for learned image registration

2020-11-11 · Steffen Czolbe, Oswin Krause, Aasa Feragen

We propose a semantic similarity metric for image registration. Existing metrics like euclidean distance or normalized cross-correlation focus on aligning intensity values, giving difficulties with low intensity contrast or noise. Our semantic approach learns dataset-specific features that drive the optimization of a learning-based registration model. Comparing to existing unsupervised and supervised methods across multiple image modalities and applications, we achieve consistently high registration accuracy and faster convergence than state of the art, and the learned invariance to noise gives smoother transformations on low-quality images.

📄 PDF Abstract BibTeX arXiv:2011.05735

Code (1)

SteffenCzolbe/DeepSimRegistration pytorch

Tasks

Image RegistrationSemantic SimilaritySemantic Textual Similarity

Similar Papers 제목 키워드 기반

Generating Images with Perceptual Similarity Metrics based on Deep Networks

2016-02-08 · NeurIPS 2016 12 · Alexey Dosovitskiy, Thomas Brox

Image-generating machine learning models are typically trained with loss functions based on distance in the image space. This often leads to over-smoothed results. We propose a class of loss functions, which we call deep…

Image Generation

Multi-view dense image matching with similarity learning and geometry priors

2025-05-16 · Mohamed Ali Chebbi, Ewelina Rupnik, Paul Lopes, Marc Pierrot-Deseilligny

We introduce MV-DeepSimNets, a comprehensive suite of deep neural networks designed for multi-view similarity learning, leveraging epipolar geometry for training. Our approach incorporates an online geometry prior to cha…

Surface Reconstruction

DeepSim-Nets: Deep Similarity Networks for Stereo Image Matching

2023-04-17 · Mohamed Ali Chebbi, Ewelina Rupnik, Marc Pierrot-Deseilligny, Paul Lopes

We present three multi-scale similarity learning architectures, or DeepSim networks. These models learn pixel-level matching with a contrastive loss and are agnostic to the geometry of the considered scene. We establish …

DeepSim: A Reinforcement Learning Environment Build Toolkit for ROS and Gazebo

2022-05-17 · Woong Gyu La, Lingjie Kong, Sunil Muralidhara, Pratik Nichat

We propose DeepSim, a reinforcement learning environment build toolkit for ROS and Gazebo. It allows machine learning or reinforcement learning researchers to access the robotics domain and create complex and challenging…

BIG-bench Machine Learningreinforcement-learningReinforcement LearningReinforcement Learning (RL)

Semantic similarity metrics for learned image registration

2021-04-20 · Steffen Czolbe, Oswin Krause, Aasa Feragen

We propose a semantic similarity metric for image registration. Existing metrics like Euclidean Distance or Normalized Cross-Correlation focus on aligning intensity values, giving difficulties with low intensity contrast…

Image RegistrationSemantic SimilaritySemantic Textual Similarity