Patch Matching
32 papers with code • 2 benchmarks • 4 datasets
Latest papers
Reconstructing occluded Elevation Information in Terrain Maps with Self-supervised Learning
We first evaluate a supervised learning approach on synthetic data for which we have the full ground-truth available and subsequently move to several real-world datasets.
CANet: A Context-Aware Network for Shadow Removal
In this paper, we propose a novel two-stage context-aware network named CANet for shadow removal, in which the contextual information from non-shadow regions is transferred to shadow regions at the embedded feature spaces.
Patch Craft: Video Denoising by Deep Modeling and Patch Matching
Our algorithm augments video sequences with patch-craft frames and feeds them to a CNN.
Attention-Based Multimodal Image Matching
We propose an attention-based approach for multimodal image patch matching using a Transformer encoder attending to the feature maps of a multiscale Siamese CNN.
HyNet: Learning Local Descriptor with Hybrid Similarity Measure and Triplet Loss
Recent works show that local descriptor learning benefits from the use of L2 normalisation, however, an in-depth analysis of this effect lacks in the literature.
Naive-Student: Leveraging Semi-Supervised Learning in Video Sequences for Urban Scene Segmentation
We view this work as a notable step towards building a simple procedure to harness unlabeled video sequences and extra images to surpass state-of-the-art performance on core computer vision tasks.
On Translation Invariance in CNNs: Convolutional Layers can Exploit Absolute Spatial Location
In this paper we challenge the common assumption that convolutional layers in modern CNNs are translation invariant.
SOLAR: Second-Order Loss and Attention for Image Retrieval
One is focused on second-order spatial information to increase the performance of image descriptors, both local and global.
Semi-Supervised Learning for Face Sketch Synthesis in the Wild
Instead of supervising the network with ground truth sketches, we first perform patch matching in feature space between the input photo and photos in a small reference set of photo-sketch pairs.
CrossNet: An End-to-end Reference-based Super Resolution Network using Cross-scale Warping
The Reference-based Super-resolution (RefSR) super-resolves a low-resolution (LR) image given an external high-resolution (HR) reference image, where the reference image and LR image share similar viewpoint but with significant resolution gap x8.