Related papers: SfM-Net: Learning of Structure and Motion from Vid…

Autonomous vehicles and robots require a full scene understanding of the environment to interact with it. Such a perception typically incorporates pixel-wise knowledge of the depths and semantic labels for each image from a video sensor.…

How to effectively explore spatial-temporal features is important for video colorization. Instead of stacking multiple frames along the temporal dimension or recurrently propagating estimated features that will accumulate errors or cannot…

This paper addresses fast semantic segmentation on video.Video segmentation often calls for real-time, or even fasterthan real-time, processing. One common recipe for conserving computation arising from feature extraction is to propagate…

Semantic segmentation is a fundamental task in multimedia processing, which can be used for analyzing, understanding, editing contents of images and videos, among others. To accelerate the analysis of multimedia data, existing segmentation…

Motion compensation is one of the most essential methods for any video compression algorithm. Video frame prediction is a task analogous to motion compensation. In recent years, the task of frame prediction is undertaken by deep neural…

We present a diffeomorphic image registration algorithm to learn spatial transformations between pairs of images to be registered using fully convolutional networks (FCNs) under a self-supervised learning setting. The network is trained to…

We address the problem of semantic correspondence, that is, establishing a dense flow field between images depicting different instances of the same object or scene category. We propose to use images annotated with binary foreground masks…

We propose a learning-based method that solves monocular stereo and can be extended to fuse depth information from multiple target frames. Given two unconstrained images from a monocular camera with known intrinsic calibration, our network…

This paper presents a deep learning framework for medical video segmentation. Convolution neural network (CNN) and transformer-based methods have achieved great milestones in medical image segmentation tasks due to their incredible semantic…

Most of current Convolution Neural Network (CNN) based methods for optical flow estimation focus on learning optical flow on synthetic datasets with groundtruth, which is not practical. In this paper, we propose an unsupervised optical flow…

In this paper, we study the problem of 3D scene geometry decomposition and manipulation from 2D views. By leveraging the recent implicit neural representation techniques, particularly the appealing neural radiance fields, we introduce an…

Existing deep methods produce highly accurate 3D reconstructions in stereo and multiview stereo settings, i.e., when cameras are both internally and externally calibrated. Nevertheless, the challenge of simultaneous recovery of camera poses…

Most Video Super-Resolution (VSR) methods enhance a video reference frame by aligning its neighboring frames and mining information on these frames. Recently, deformable alignment has drawn extensive attention in VSR community for its…

3D reconstruction of dynamic scenes is a long-standing problem in computer graphics and increasingly difficult the less information is available. Shape-from-Template (SfT) methods aim to reconstruct a template-based geometry from RGB images…

Videos can be manipulated by duplicating a sequence of consecutive frames with the goal of concealing or imitating a specific content in the same video. In this paper, we propose a novel coarse-to-fine framework based on deep Convolutional…

We present a novel framework for self-supervised grasped object segmentation with a robotic manipulator. Our method successively learns an agnostic foreground segmentation followed by a distinction between manipulator and object solely by…

Perceiving 3D objects from monocular inputs is crucial for robotic systems, given its economy compared to multi-sensor settings. It is notably difficult as a single image can not provide any clues for predicting absolute depth values.…

Scene regression methods, such as VGGT, solve the Structure-from-Motion (SfM) problem by directly regressing camera poses and 3D scene structures from input images. They demonstrate impressive performance in handling images under extreme…

We introduce SE3-Nets, which are deep neural networks designed to model and learn rigid body motion from raw point cloud data. Based only on sequences of depth images along with action vectors and point wise data associations, SE3-Nets…

Contextual information can have a substantial impact on the performance of visual tasks such as semantic segmentation, object detection, and geometric estimation. Data stored in Geographic Information Systems (GIS) offers a rich source of…