Related papers: Point upsampling networks for single-photon sensin…
Image restoration requires simultaneously preserving fine-grained local structures and maintaining long-range spatial coherence. While convolutional networks struggle with limited receptive fields, and Transformers incur quadratic…
Recently, feature upsampling has gained increasing attention owing to its effectiveness in enhancing vision foundation models (VFMs) for pixel-level understanding tasks. Existing methods typically rely on high-resolution features from the…
We present an improved version of PointRCNN for 3D object detection, in which a multi-branch backbone network is adopted to handle the non-uniform density of point clouds. An uncertainty-based sampling policy is proposed to deal with the…
The traditional ingle-scale U-Net often leads to the loss of spatial information during deblurring, which affects the deblurring accracy. Additionally, due to the convolutional method's limitation in capturing long-range dependencies, the…
Recently, 3D LiDAR has emerged as a promising technique in the field of gait-based person identification, serving as an alternative to traditional RGB cameras, due to its robustness under varying lighting conditions and its ability to…
With the development of Deep Neural Networks (DNNs), plenty of methods based on DNNs have been proposed for Single Image Super-Resolution (SISR). However, existing methods mostly train the DNNs on uniformly sampled LR-HR patch pairs, which…
Point cloud upsampling is crucial for tasks like 3D reconstruction. While existing methods rely on patch-based inputs, and there is no research discussing the differences and principles between point cloud model full input and patch based…
Point cloud sampling plays a crucial role in reducing computation costs and storage requirements for various vision tasks. Traditional sampling methods, such as farthest point sampling, lack task-specific information and, as a result,…
Image classification is a core task of intelligent sensing, conventionally follows a sequential imaging then processing pipeline. However, redundant high-dimensional image reconstruction is inherently inefficient, especially in photon…
Recently, state space models (SSM), particularly Mamba, have attracted significant attention from scholars due to their ability to effectively balance computational efficiency and performance. However, most existing visual Mamba methods…
Spectral imaging technologies have rapidly evolved during the past decades. The recent development of single-camera-one-shot techniques for hyperspectral imaging allows multiple spectral bands to be captured simultaneously (3x3, 4x4 or 5x5…
Current Point-based detectors can only learn from the provided points, with limited receptive fields and insufficient global learning capabilities for such targets. In this paper, we present a novel Point Dilation Mechanism for single-stage…
Semantic segmentation of aerial point cloud data can be utilised to differentiate which points belong to classes such as ground, buildings, or vegetation. Point clouds generated from aerial sensors mounted to drones or planes can utilise…
Accurate modelling of the effective point spread function (ePSF) is essential for high-precision photometry and astrometry, particularly in undersampled imaging regimes. In this work, we build on a well-established ePSF modelling framework…
Shadow removal aims to restore images that are partially degraded by shadows, where the degradation is spatially localized and non-uniform. Unlike general restoration tasks that assume global degradation, shadow removal can leverage…
Despite diffusion models' superior capabilities in modeling complex distributions, there are still non-trivial distributional discrepancies between generated and ground-truth images, which has resulted in several notable problems in image…
This paper proposes a novel point-cloud-based place recognition system that adopts a deep learning approach for feature extraction. By using a convolutional neural network pre-trained on color images to extract features from a range image…
Deep unfolding networks have gained increasing attention in the field of compressed sensing (CS) owing to their theoretical interpretability and superior reconstruction performance. However, most existing deep unfolding methods often face…
Pan-sharpening is a process of merging a high-resolution (HR) panchromatic (PAN) image and its corresponding low-resolution (LR) multi-spectral (MS) image to create an HR-MS and pan-sharpened image. However, due to the different sensors'…
We present PointAugment, a new auto-augmentation framework that automatically optimizes and augments point cloud samples to enrich the data diversity when we train a classification network. Different from existing auto-augmentation methods…