Related papers: Self-Supervised Learning of Depth and Camera Motio…
Recent depth foundation models trained on perspective imagery achieve strong performance, yet generalize poorly to 360$^\circ$ images due to the substantial geometric discrepancy between perspective and panoramic domains. Moreover, fully…
Self-supervised monocular depth and ego-motion estimation is a promising approach to replace or supplement expensive depth sensors such as LiDAR for robotics applications like autonomous driving. However, most research in this area focuses…
The success of deep neural networks generally requires a vast amount of training data to be labeled, which is expensive and unfeasible in scale, especially for video collections. To alleviate this problem, in this paper, we propose…
In this work we present a self-supervised learning framework to simultaneously train two Convolutional Neural Networks (CNNs) to predict depth and surface normals from a single image. In contrast to most existing frameworks which represent…
We present a new learning-based method for multi-frame depth estimation from a color video, which is a fundamental problem in scene understanding, robot navigation or handheld 3D reconstruction. While recent learning-based methods estimate…
Self-supervised learning has drawn attention through its effectiveness in learning in-domain representations with no ground-truth annotations; in particular, it is shown that properly designed pretext tasks (e.g., contrastive prediction…
Self-supervised prediction is a powerful mechanism to learn representations that capture the underlying structure of the data. Despite recent progress, the self-supervised video prediction task is still challenging. One of the critical…
We propose a method for self-supervised image representation learning under the guidance of 3D geometric consistency. Our intuition is that 3D geometric consistency priors such as smooth regions and surface discontinuities may imply…
We present an algorithm for estimating consistent dense depth maps and camera poses from a monocular video. We integrate a learning-based depth prior, in the form of a convolutional neural network trained for single-image depth estimation,…
Presenting context images to a viewer's peripheral vision is one of the most effective techniques to enhance immersive visual experiences. However, most images only present a narrow view, since the field-of-view (FoV) of standard cameras is…
In this paper, we propose a learning-based method for predicting dense depth values of a scene from a monocular omnidirectional image. An omnidirectional image has a full field-of-view, providing much more complete descriptions of the scene…
360{\deg} images and videos have become an economic and popular way to provide VR experiences using real-world content. However, the manipulation of the stereo panoramic content remains less explored. In this paper, we focus on the…
Self-supervised depth estimation has drawn much attention in recent years as it does not require labeled data but image sequences. Moreover, it can be conveniently used in various applications, such as autonomous driving, robotics,…
Despite significant progress made in the past few years, challenges remain for depth estimation using a single monocular image. First, it is nontrivial to train a metric-depth prediction model that can generalize well to diverse scenes…
Unsupervised learning based depth estimation methods have received more and more attention as they do not need vast quantities of densely labeled data for training which are touch to acquire. In this paper, we propose a novel unsupervised…
Omnidirectional and 360{\deg} images are becoming widespread in industry and in consumer society, causing omnidirectional computer vision to gain attention. Their wide field of view allows the gathering of a great amount of information…
Omnidirectional (360-degree) video is rapidly gaining popularity due to advancements in immersive technologies like virtual reality (VR) and extended reality (XR). However, real-time streaming of such videos, especially in live mobile…
Supervised deep learning often suffers from the lack of sufficient training data. Specifically in the context of monocular depth map prediction, it is barely possible to determine dense ground truth depth images in realistic dynamic outdoor…
3D photography renders a static image into a video with appealing 3D visual effects. Existing approaches typically first conduct monocular depth estimation, then render the input frame to subsequent frames with various viewpoints, and…
In this paper we propose USegScene, a framework for semantically guided unsupervised learning of depth, optical flow and ego-motion estimation for stereo camera images using convolutional neural networks. Our framework leverages semantic…