Related papers: PanoFormer: Panorama Transformer for Indoor 360 De…

Omnidirectional vision is becoming increasingly relevant as more efficient $360^o$ image acquisition is now possible. However, the lack of annotated $360^o$ datasets has hindered the application of deep learning techniques on spherical…

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…

The Depth-aware Video Panoptic Segmentation (DVPS) is a new challenging vision problem that aims to predict panoptic segmentation and depth in a video simultaneously. The previous work solves this task by extending the existing panoptic…

In this work, we present Multiformer, a novel approach to depth-aware video panoptic segmentation (DVPS) based on the mask transformer paradigm. Our method learns object representations that are shared across segmentation, monocular depth…

360{\deg} spherical images have advantages of wide view field, and are typically projected on a planar plane for processing, which is known as equirectangular image. The object shape in equirectangular images can be distorted and lack…

Depth estimation plays a pivotal role in advancing human-robot interactions, especially in indoor environments where accurate 3D scene reconstruction is essential for tasks like navigation and object handling. Monocular depth estimation,…

Vision Transformers face a fundamental limitation: standard self-attention jointly processes spatial and channel dimensions, leading to entangled representations that prevent independent modeling of structural and semantic dependencies.…

This paper presents a Refinement Pyramid Transformer (RePFormer) for robust facial landmark detection. Most facial landmark detectors focus on learning representative image features. However, these CNN-based feature representations are not…

3D room layout estimation by a single panorama using deep neural networks has made great progress. However, previous approaches can not obtain efficient geometry awareness of room layout with the only latitude of boundaries or…

The convolutional neural network-based methods have become more and more popular for medical image segmentation due to their outstanding performance. However, they struggle with capturing long-range dependencies, which are essential for…

Transformers have shown impressive performance in various natural language processing and computer vision tasks, due to the capability of modeling long-range dependencies. Recent progress has demonstrated that combining such Transformers…

Monocular depth estimation using Convolutional Neural Networks (CNNs) has shown impressive performance in outdoor driving scenes. However, self-supervised learning of indoor depth from monocular sequences is quite challenging for…

Learned image compression methods have exhibited superior rate-distortion performance than classical image compression standards. Most existing learned image compression models are based on Convolutional Neural Networks (CNNs). Despite…

Visual place recognition is a challenging task in the field of computer vision, and autonomous robotics and vehicles, which aims to identify a location or a place from visual inputs. Contemporary methods in visual place recognition employ…

Monocular depth estimation in colonoscopy video aims to overcome the unusual lighting properties of the colonoscopic environment. One of the major challenges in this area is the domain gap between annotated but unrealistic synthetic data…

Current stereo matching techniques are challenged by restricted searching space, occluded regions and sheer size. While single image depth estimation is spared from these challenges and can achieve satisfactory results with the extracted…

Convolutional neural networks (CNNs) have shown promising results on several segmentation tasks in magnetic resonance (MR) images. However, the accuracy of CNNs may degrade severely when segmenting images acquired with different scanners…

The depth completion task is a critical problem in autonomous driving, involving the generation of dense depth maps from sparse depth maps and RGB images. Most existing methods employ a spatial propagation network to iteratively refine the…

Learning to reconstruct depths in a single image by watching unlabeled videos via deep convolutional network (DCN) is attracting significant attention in recent years. In this paper, we introduce a surface normal representation for…

Understanding the mechanisms underlying deep neural networks remains a fundamental challenge in machine learning and computer vision. One promising, yet only preliminarily explored approach, is feature inversion, which attempts to…