Related papers: Disentangled Human Body Representation Based on Un…
Automatic estimation of 3D human pose from monocular RGB images is a challenging and unsolved problem in computer vision. In a supervised manner, approaches heavily rely on laborious annotations and present hampered generalization ability…
Recent works have shown how realistic talking face images can be obtained under the supervision of geometry guidance, e.g., facial landmark or boundary. To alleviate the demand for manual annotations, in this paper, we propose a novel…
We present a scalable framework for cross-embodiment humanoid robot control by learning a shared latent representation that unifies motion across humans and diverse humanoid platforms, including single-arm, dual-arm, and legged humanoid…
Recent work has shown that object-centric representations can greatly help improve the accuracy of learning dynamics while also bringing interpretability. In this work, we take this idea one step further, ask the following question: "can…
We present deep neural network methodology to reconstruct the 3d pose and shape of people, given an input RGB image. We rely on a recently introduced, expressivefull body statistical 3d human model, GHUM, trained end-to-end, and learn to…
Machine Learning (ML) is increasingly being used for computer aided diagnosis of brain related disorders based on structural magnetic resonance imaging (MRI) data. Most of such work employs biologically and medically meaningful hand-crafted…
3D Skeleton-based human action recognition has attracted increasing attention in recent years. Most of the existing work focuses on supervised learning which requires a large number of labeled action sequences that are often expensive and…
This study addresses the problem of 3D human mesh reconstruction from multi-view images. Recently, approaches that directly estimate the skinned multi-person linear model (SMPL)-based human mesh vertices based on volumetric heatmap…
Our work focuses on unsupervised and generative methods that address the following goals: (a) learning unsupervised generative representations that discover latent factors controlling image semantic attributes, (b) studying how this ability…
Combining Generative Adversarial Networks (GANs) with encoders that learn to encode data points has shown promising results in learning data representations in an unsupervised way. We propose a framework that combines an encoder and a…
Self-supervised learning (SSL), which aims to learn meaningful prior representations from unlabeled data, has been proven effective for skeleton-based action understanding. Different from the image domain, skeleton data possesses sparser…
Progress in self-supervised learning has brought strong general image representation learning methods. Yet so far, it has mostly focused on image-level learning. In turn, tasks such as unsupervised image segmentation have not benefited from…
In this work, we focus on the task of learning and representing dense correspondences in deformable object categories. While this problem has been considered before, solutions so far have been rather ad-hoc for specific object types (i.e.,…
Manipulating images of complex scenes to reconstruct, insert and/or remove specific object instances is a challenging task. Complex scenes contain multiple semantics and objects, which are frequently cluttered or ambiguous, thus hampering…
We present a novel approach for synthesizing photo-realistic images of people in arbitrary poses using generative adversarial learning. Given an input image of a person and a desired pose represented by a 2D skeleton, our model renders the…
Despite the recent advance of Generative Adversarial Networks (GANs) in high-fidelity image synthesis, there lacks enough understanding of how GANs are able to map a latent code sampled from a random distribution to a photo-realistic image.…
Aligning multiple modalities in a latent space, such as images and texts, has shown to produce powerful semantic visual representations, fueling tasks like image captioning, text-to-image generation, or image grounding. In the context of…
Self-supervised representation learning targets to learn convnet-based image representations from unlabeled data. Inspired by the success of NLP methods in this area, in this work we propose a self-supervised approach based on spatially…
Recent progress in 4D implicit representation focuses on globally controlling the shape and motion with low dimensional latent vectors, which is prone to missing surface details and accumulating tracking error. While many deep local…
Recent monocular human performance capture approaches have shown compelling dense tracking results of the full body from a single RGB camera. However, existing methods either do not estimate clothing at all or model cloth deformation with…