相关论文: Volumetric performance capture from minimal camera…

In this paper we present a novel approach for bottom-up multi-person 3D human pose estimation from monocular RGB images. We propose to use high resolution volumetric heatmaps to model joint locations, devising a simple and effective…

With the recent successful adaptation of transformers to the vision domain, particularly when trained in a self-supervised fashion, it has been shown that vision transformers can learn impressive object-reasoning-like behaviour and features…

X-Ray imaging is quick, cheap and useful for front-line care assessment and intra-operative real-time imaging (e.g., C-Arm Fluoroscopy). However, it suffers from projective information loss and lacks vital volumetric information on which…

We present a method for fast 3D reconstruction and real-time rendering of dynamic humans from monocular videos with accompanying parametric body fits. Our method can reconstruct a dynamic human in less than 3h using a single GPU, compared…

Image compression and reconstruction are crucial for various digital applications. While contemporary neural compression methods achieve impressive compression rates, the adoption of such technology has been largely hindered by the…

The rise of capturing systems for objects and scenes in 3D with increased fidelity and immersion has led to the popularity of volumetric video contents that can be seen from any position and angle in 6 degrees of freedom navigation. Such…

Recent advances in image-based human pose estimation make it possible to capture 3D human motion from a single RGB video. However, the inherent depth ambiguity and self-occlusion in a single view prohibit the recovery of as high-quality…

There are many forms of feature information present in video data. Principle among them are object identity information which is largely static across multiple video frames, and object pose and style information which continuously…

Convolution is an efficient technique to obtain abstract feature representations using hierarchical layers in deep networks. Although performing convolution in Euclidean geometries is fairly straightforward, its extension to other…

This paper proposes a new method for live free-viewpoint human performance capture with dynamic details (e.g., cloth wrinkles) using a single RGBD camera. Our main contributions are: (i) a multi-layer representation of garments and body,…

Video forgery detection is becoming an important issue in recent years, because modern editing software provide powerful and easy-to-use tools to manipulate videos. In this paper we propose to perform detection by means of deep learning,…

Capturing and labeling camera images in the real world is an expensive task, whereas synthesizing labeled images in a simulation environment is easy for collecting large-scale image data. However, learning from only synthetic images may not…

This paper presents an investigation of vision transformer learning for multi-view geometry tasks, such as optical flow estimation, by fine-tuning video foundation models. Unlike previous methods that involve custom architectural designs…

This paper addresses key challenges in object-centric representation learning of video. While existing approaches struggle with complex scenes, we propose a novel weakly-supervised framework that emphasises geometric understanding and…

Panoptic 3D reconstruction from a monocular video is a fundamental perceptual task in robotic scene understanding. However, existing efforts suffer from inefficiency in terms of inference speed and accuracy, limiting their practical…

Despite the impressive progress of telepresence systems for room-scale scenes with static and dynamic scene entities, expanding their capabilities to scenarios with larger dynamic environments beyond a fixed size of a few square-meters…

This paper presents a novel unsupervised probabilistic model estimation of visual background in video sequences using a variational autoencoder framework. Due to the redundant nature of the backgrounds in surveillance videos, visual…

We propose a novel method to reconstruct volumetric flows from sparse views via a global transport formulation. Instead of obtaining the space-time function of the observations, we reconstruct its motion based on a single initial state. In…

Multiview video is a key data source for volumetric video, enabling immersive 3D scene reconstruction but posing significant challenges in storage and transmission due to its massive data volume. Recently, deep learning-based end-to-end…

Human motion retargeting aims to transfer the motion of one person in a "driving" video or set of images to another person. Existing efforts leverage a long training video from each target person to train a subject-specific motion transfer…