Related papers: A generalised feature for low level vision
We generalise Spatial Transformer Networks (STN) by replacing the parametric transformation of a fixed, regular sampling grid with a deformable, statistical shape model which is itself learnt. We call this a Statistical Transformer Network…
The rise of machine learning in image processing has created a gap between trainable data-driven and classical model-driven approaches: While learning-based models often show superior performance, classical ones are often more transparent.…
Human face images usually appear with wide range of visual scales. The existing face representations pursue the bandwidth of handling scale variation via multi-scale scheme that assembles a finite series of predefined scales. Such…
The concept of measurement in classical scattering is interpreted as an overlap of a particle packet with some area in phase space that describes the detector. Considering that usually we record the passage of particles at some point in…
We introduce a multi-scale framework for low-level vision, where the goal is estimating physical scene values from image data---such as depth from stereo image pairs. The framework uses a dense, overlapping set of image regions at multiple…
Image segmentation, a key task in computer vision, has traditionally relied on convolutional neural networks (CNNs), yet these models struggle with capturing complex spatial dependencies, objects with varying scales, need for manually…
As weak lensing surveys become deeper, they reveal more non-Gaussian aspects of the convergence field which can only be extracted using statistics beyond the power spectrum. In Cheng et al. (2020) we showed that the scattering transform, a…
Feature means countenance, remote sensing scene objects with similar characteristics, associated to interesting scene elements in the image formation process. They are classified into three types in image processing, that is low, middle and…
Vision-language models like CLIP can offer a promising foundation for 3D scene understanding when extended with 3D tokenizers. However, standard approaches, such as k-nearest neighbor or radius-based tokenization, struggle with cross-domain…
We introduce a bottom-up model for simultaneously finding many boundary elements in an image, including contours, corners and junctions. The model explains boundary shape in each small patch using a 'generalized M-junction' comprising M…
Point scene understanding is a challenging task to process real-world scene point cloud, which aims at segmenting each object, estimating its pose, and reconstructing its mesh simultaneously. Recent state-of-the-art method first segments…
Convolutional neural networks (CNNs) have rapidly risen in popularity for many machine learning applications, particularly in the field of image recognition. Much of the benefit generated from these networks comes from their ability to…
Convolutional neural network (CNN) has led to significant progress in object detection. In order to detect the objects in various sizes, the object detectors often exploit the hierarchy of the multi-scale feature maps called feature…
Image identification is one of the most challenging tasks in different areas of computer vision. Scale-invariant feature transform is an algorithm to detect and describe local features in images to further use them as an image matching…
The tradeoff between receptive field size and efficiency is a crucial issue in low level vision. Plain convolutional networks (CNNs) generally enlarge the receptive field at the expense of computational cost. Recently, dilated filtering has…
Advanced visual localization techniques encompass image retrieval challenges and 6 Degree-of-Freedom (DoF) camera pose estimation, such as hierarchical localization. Thus, they must extract global and local features from input images.…
Segmenting unseen objects from images is a critical perception skill that a robot needs to acquire. In robot manipulation, it can facilitate a robot to grasp and manipulate unseen objects. Mean shift clustering is a widely used method for…
Every Scene Text Recognition (STR) task consists of text localization \& text recognition as the prominent sub-tasks. However, in real-world applications with fixed camera positions such as equipment monitor reading, image-based data entry,…
Most popular hand-crafted key-point detectors such as Harris corner, SIFT, SURF aim to detect corners, blobs, junctions or other human defined structures in images. Though being robust with some geometric transformations, unintended…
The paper presents a new model for single channel images low-level interpretation. The image is decomposed into a graph which captures a complete set of structural features. The description allows to accurately identify every edge location…