相关论文: CHOSEN: Contrastive Hypothesis Selection for Multi…

Unsupervised cross-spectral stereo matching aims at recovering disparity given cross-spectral image pairs without any supervision in the form of ground truth disparity or depth. The estimated depth provides additional information…

Previous monocular depth estimation methods take a single view and directly regress the expected results. Though recent advances are made by applying geometrically inspired loss functions during training, the inference procedure does not…

Depth estimation is solved as a regression or classification problem in existing learning-based multi-view stereo methods. Although these two representations have recently demonstrated their excellent performance, they still have apparent…

Deep learning has recently demonstrated its excellent performance on the task of multi-view stereo (MVS). However, loss functions applied for deep MVS are rarely studied. In this paper, we first analyze existing loss functions' properties…

In stereo-matching knowledge distillation methods of the self-supervised monocular depth estimation, the stereo-matching network's knowledge is distilled into a monocular depth network through pseudo-depth maps. In these methods, the…

Stereo matching is an essential basis for various applications, but most stereo matching methods have poor generalization performance and require a fixed disparity search range. Moreover, current stereo matching methods focus on the scenes…

Multi-view feature extraction is an efficient approach for alleviating the issue of dimensionality in highdimensional multi-view data. Contrastive learning (CL), which is a popular self-supervised learning method, has recently attracted…

Estimating depth from RGB images is a long-standing ill-posed problem, which has been explored for decades by the computer vision, graphics, and machine learning communities. Among the existing techniques, stereo matching remains one of the…

In speaker verification, contrastive learning is gaining popularity as an alternative to the traditionally used classification-based approaches. Contrastive methods can benefit from an effective use of hard negative pairs, which are…

In this paper, we propose a dense depth estimation pipeline for multiview 360{\deg} images. The proposed pipeline leverages a spherical camera model that compensates for radial distortion in 360{\deg} images. The key contribution of this…

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…

Purpose: Stereo matching methods that enable depth estimation are crucial for visualization enhancement applications in computer-assisted surgery (CAS). Learning-based stereo matching methods are promising to predict accurate results on…

Vision Transformers (ViTs) represent a groundbreaking shift in machine learning approaches to computer vision. Unlike traditional approaches, ViTs employ the self-attention mechanism, which has been widely used in natural language…

We describe a method for unpaired realistic depth synthesis that learns diverse variations from the real-world depth scans and ensures geometric consistency between the synthetic and synthesized depth. The synthesized realistic depth can…

Existing approaches for multi-view multi-person 3D pose estimation explicitly establish cross-view correspondences to group 2D pose detections from multiple camera views and solve for the 3D pose estimation for each person. Establishing…

This paper introduces a novel deep framework for dense 3D reconstruction from multiple image frames, leveraging a sparse set of depth measurements gathered jointly with image acquisition. Given a deep multi-view stereo network, our…

Disparity/depth estimation from sequences of stereo images is an important element in 3D vision. Owing to occlusions, imperfect settings and homogeneous luminance, accurate estimate of depth remains a challenging problem. Targetting view…

We propose a selective learning method using meta-learning and deep reinforcement learning for medical image interpretation in the setting of limited labeling resources. Our method, MedSelect, consists of a trainable deep learning selector…

Recent techniques in self-supervised monocular depth estimation are approaching the performance of supervised methods, but operate in low resolution only. We show that high resolution is key towards high-fidelity self-supervised monocular…

Reconstructing the 3D shape of an object using several images under different light sources is a very challenging task, especially when realistic assumptions such as light propagation and attenuation, perspective viewing geometry and…