Related papers: ZoeDepth: Zero-shot Transfer by Combining Relative…

Accurate surround-view depth estimation provides a competitive alternative to laser-based sensors and is essential for 3D scene understanding in autonomous driving. While empirical studies have proposed various approaches that primarily…

Meta-learning aims at learning quickly on novel tasks with limited data by transferring generic experience learned from previous tasks. Naturally, few-shot learning has been one of the most popular applications for meta-learning. However,…

Depth estimation is a cornerstone of 3D reconstruction and plays a vital role in minimally invasive endoscopic surgeries. However, most current depth estimation networks rely on traditional convolutional neural networks, which are limited…

One-shot image classification aims to train image classifiers over the dataset with only one image per category. It is challenging for modern deep neural networks that typically require hundreds or thousands of images per class. In this…

Monocular depth estimation is a challenging task in complex compositions depicting multiple objects of diverse scales. Albeit the recent great progress thanks to the deep convolutional neural networks (CNNs), the state-of-the-art monocular…

In this paper, different techniques of few-shot, zero-shot, and regular object detection have been investigated. The need for few-shot learning and zero-shot learning techniques is crucial and arises from the limitations and challenges in…

Currently, the state-of-the-art methods treat few-shot semantic segmentation task as a conditional foreground-background segmentation problem, assuming each class is independent. In this paper, we introduce the concept of meta-class, which…

Due to the lack of properly annotated medical data, exploring the generalization capability of the deep model is becoming a public concern. Zero-shot learning (ZSL) has emerged in recent years to equip the deep model with the ability to…

Due to their text-to-image synthesis feature, diffusion models have recently seen a rise in visual perception tasks, such as depth estimation. The lack of good-quality datasets makes the extraction of a fine-grain semantic context…

Omnidirectional depth sensing has its advantage over the conventional stereo systems since it enables us to recognize the objects of interest in all directions without any blind regions. In this paper, we propose a novel wide-baseline…

Self-supervised depth estimation from monocular cameras in diverse outdoor conditions, such as daytime, rain, and nighttime, is challenging due to the difficulty of learning universal representations and the severe lack of labeled…

Bokeh rendering and depth estimation share a fundamental optical connection, yet existing methods fail to fully exploit this reciprocity. Conventional bokeh pipelines rely heavily on noisy depth maps that inevitably introduce visual…

Given stereo or egomotion image pairs, a popular and successful method for unsupervised learning of monocular depth estimation is to measure the quality of image reconstructions resulting from the learned depth predictions. Continued…

Monocular depth estimation (MDE) aims to transform an RGB image of a scene into a pixelwise depth map from the same camera view. It is fundamentally ill-posed due to missing information: any single image can have been taken from many…

Monocular depth estimation has been increasingly adopted in robotics and autonomous driving for its ability to infer scene geometry from a single camera. In self-supervised monocular depth estimation frameworks, the network jointly…

Quantization is a key technique to reduce network size and computational complexity by representing the network parameters with a lower precision. Traditional quantization methods rely on access to original training data, which is often…

We present a novel approach for metric dense depth estimation based on the fusion of a single-view image and a sparse, noisy Radar point cloud. The direct fusion of heterogeneous Radar and image data, or their encodings, tends to yield…

The goal of object-centric representation learning is to decompose visual scenes into a structured representation that isolates the entities. Recent successes have shown that object-centric representation learning can be scaled to…

We design a multiscopic vision system that utilizes a low-cost monocular RGB camera to acquire accurate depth estimation. Unlike multi-view stereo with images captured at unconstrained camera poses, the proposed system controls the motion…

A significant shortcoming of current state-of-the-art (SOTA) named-entity recognition (NER) systems is their lack of generalization to unseen domains, which poses a major problem since obtaining labeled data for NER in a new domain is…