Related papers: Box2Poly: Memory-Efficient Polygon Prediction of A…

Recent scene text detection works mainly focus on curve text detection. However, in real applications, the curve texts are more scarce than the multi-oriented ones. Accurate detection of multi-oriented text with large variations of scales,…

Establishing robust and accurate correspondences is a fundamental backbone to many computer vision algorithms. While recent learning-based feature matching methods have shown promising results in providing robust correspondences under…

Detection and tracking of moving objects is an essential component in environmental perception for autonomous driving. In the flourishing field of multi-view 3D camera-based detectors, different transformer-based pipelines are designed to…

The growing demand for high-resolution maps across various applications has underscored the necessity of accurately segmenting building vectors from overhead imagery. However, current deep neural networks often produce raster data outputs,…

Convolutional neural networks (CNNs) have demonstrated their superiority in numerous computer vision tasks, yet their computational cost results prohibitive for many real-time applications such as pedestrian detection which is usually…

Sparse R-CNN is a recent strong object detection baseline by set prediction on sparse, learnable proposal boxes and proposal features. In this work, we propose to improve Sparse R-CNN with two dynamic designs. First, Sparse R-CNN adopts a…

In a previous paper it was shown that a machine learning regression problem can be solved within the framework of random function theory, with the optimal kernel analytically derived from symmetry and indifference principles and coinciding…

One of the main challenges for arbitrary-shaped text detection is to design a good text instance representation that allows networks to learn diverse text geometry variances. Most of existing methods model text instances in image spatial…

DensePose estimation task is a significant step forward for enhancing user experience computer vision applications ranging from augmented reality to cloth fitting. Existing neural network models capable of solving this task are heavily…

Sparse auto-encoders are useful for extracting low-dimensional representations from high-dimensional data. However, their performance degrades sharply when the input noise at test time differs from the noise employed during training. This…

Direct contour regression for instance segmentation is a challenging task. Previous works usually achieve it by learning to progressively refine the contour prediction or adopting a shape representation with limited expressiveness. In this…

Existing techniques for text detection can be broadly classified into two primary groups: segmentation-based and regression-based methods. Segmentation models offer enhanced robustness to font variations but require intricate…

Region-based Convolutional Neural Networks (R-CNNs) have achieved great success in the field of object detection. The existing R-CNNs usually divide a Region-of-Interest (ROI) into grids, and then localize objects by utilizing the spatial…

In pose estimation for seen objects, a prevalent pipeline involves using neural networks to predict dense 3D coordinates of the object surface on 2D images, which are then used to establish dense 2D-3D correspondences. However, current…

Text in natural images is of arbitrary orientations, requiring detection in terms of oriented bounding boxes. Normally, a multi-oriented text detector often involves two key tasks: 1) text presence detection, which is a classification…

Nowadays, scene text recognition has attracted more and more attention due to its diverse applications. Most state-of-the-art methods adopt an encoder-decoder framework with the attention mechanism, autoregressively generating text from…

Latest diffusion models have shown promising results in category-level 6D object pose estimation by modeling the conditional pose distribution with depth image input. The existing methods, however, suffer from slow convergence during…

Transformers can generate predictions in two approaches: 1. auto-regressively by conditioning each sequence element on the previous ones, or 2. directly produce an output sequences in parallel. While research has mostly explored upon this…

Extraction of building footprint polygons from remotely sensed data is essential for several urban understanding tasks such as reconstruction, navigation, and mapping. Despite significant progress in the area, extracting accurate polygonal…

In computer vision pixelwise dense prediction is the task of predicting a label for each pixel in the image. Convolutional neural networks achieve good performance on this task, while being computationally efficient. In this paper we carry…