Related papers: A Refreshed Similarity-based Upsampler for Direct …
Pre-trained vision foundation models (VFMs) provide strong semantic representations, yet their patch-level features are inherently coarse, limiting their effectiveness on tasks requiring fine-grained localization, dense prediction, and…
We introduce the notion of point affiliation into feature upsampling. By abstracting a feature map into non-overlapped semantic clusters formed by points of identical semantic meaning, feature upsampling can be viewed as point affiliation…
Hyperspectral imaging (HSI) provides rich spatial-spectral information but remains costly to acquire due to hardware limitations and the difficulty of reconstructing three-dimensional data from compressed measurements. Although compressive…
Recently, single-image super-resolution has made great progress owing to the development of deep convolutional neural networks (CNNs). The vast majority of CNN-based models use a pre-defined upsampling operator, such as bicubic…
High-dimensional data is commonly encountered in numerous data analysis tasks. Feature selection techniques aim to identify the most representative features from the original high-dimensional data. Due to the absence of class label…
Fusion-based hyperspectral image super-resolution aims to fuse low-resolution hyperspectral images (LR-HSIs) and high-resolution multispectral images (HR-MSIs) to reconstruct high spatial and high spectral resolution images. Current methods…
The goal of Feature Selection - comprising filter, wrapper, and embedded approaches - is to find the optimal feature subset for designated downstream tasks. Nevertheless, current feature selection methods are limited by: 1) the selection…
A major challenge for high dynamic range (HDR) image reconstruction from multi-exposed low dynamic range (LDR) images, especially with dynamic scenes, is the extraction and merging of relevant contextual features in order to suppress any…
Typical person re-identification (re-ID) methods train a deep CNN to extract deep features and combine them with a distance metric for the final evaluation. In this work, we focus on exploiting the full information encoded in the deep…
Similarity graphs are an active research direction for the nearest neighbor search (NNS) problem. New algorithms for similarity graph construction are continuously being proposed and analyzed by both theoreticians and practitioners.…
Image resampling is a basic technique that is widely employed in daily applications, such as camera photo editing. Recent deep neural networks (DNNs) have made impressive progress in performance by introducing learned data priors. Still,…
We introduce a novel matching algorithm, called DeepMatching, to compute dense correspondences between images. DeepMatching relies on a hierarchical, multi-layer, correlational architecture designed for matching images and was inspired by…
To increase the flexibility and scalability of deep neural networks for image reconstruction, a framework is proposed based on bandpass filtering. For many applications, sensing measurements are performed indirectly. For example, in…
High-dimensional similarity search underpins modern retrieval systems, yet uniform search strategies fail to exploit the heterogeneous nature of real-world query distributions. We present an adaptive prefiltering framework that leverages…
Reconstructing a dynamic scene from image inputs is a fundamental computer vision task with many downstream applications. Despite recent advancements, existing approaches still struggle to achieve high-quality reconstructions from unseen…
Accurate upsampling of Head-Related Transfer Functions (HRTFs) from sparse measurements is crucial for personalized spatial audio rendering. Traditional interpolation methods, such as kernel-based weighting or basis function expansions,…
Recent work showed neural-network-based approaches to reconstructing images from compressively sensed measurements offer significant improvements in accuracy and signal compression. Such methods can dramatically boost the capability of…
Dense pixel matching is required for many computer vision algorithms such as disparity, optical flow or scene flow estimation. Feature Pyramid Networks (FPN) have proven to be a suitable feature extractor for CNN-based dense matching tasks.…
Learning and analyzing 3D point clouds with deep networks is challenging due to the sparseness and irregularity of the data. In this paper, we present a data-driven point cloud upsampling technique. The key idea is to learn multi-level…
Feature reassembly, i.e. feature downsampling and upsampling, is a key operation in a number of modern convolutional network architectures, e.g., residual networks and feature pyramids. Its design is critical for dense prediction tasks such…