DeepSim: Semantic similarity metrics for learned image registration
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.
Code (1)
Tasks
Image RegistrationSemantic SimilaritySemantic Textual SimilaritySimilar Papers 제목 키워드 기반
Generating Images with Perceptual Similarity Metrics based on Deep Networks
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 GenerationMulti-view dense image matching with similarity learning and geometry priors
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 ReconstructionDeepSim-Nets: Deep Similarity Networks for Stereo Image Matching
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
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
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