Related papers: Disentangling 3D Attributes from a Single 2D Image…

Reconstructing 3D human heads in low-view settings presents technical challenges, mainly due to the pronounced risk of overfitting with limited views and high-frequency signals. To address this, we propose geometry decomposition and adopt a…

Human perception is structured around objects which form the basis for our higher-level cognition and impressive systematic generalization abilities. Yet most work on representation learning focuses on feature learning without even…

Reconstructing 3D clothed humans from monocular images and videos is a fundamental problem with applications in virtual try-on, avatar creation, and mixed reality. Despite significant progress in human body recovery, accurately…

Large vision models based in deep learning architectures have been consistently advancing the state-of-the-art in biometric recognition. However, three weaknesses are commonly reported for such kind of approaches: 1) their extreme demands…

Recent 3D face reconstruction methods reconstruct the entire head compared to earlier approaches which only model the face. Although these methods accurately reconstruct facial features, they do not explicitly regulate the upper part of the…

Template 3D shapes are useful for many tasks in graphics and vision, including fitting observation data, analyzing shape collections, and transferring shape attributes. Because of the variety of geometry and topology of real-world shapes,…

The combination of deep learning, artist-curated scans, and Implicit Functions (IF), is enabling the creation of detailed, clothed, 3D humans from images. However, existing methods are far from perfect. IF-based methods recover free-form…

Most existing methods of 3D clothed human reconstruction from a single image treat the clothed human as a single object without distinguishing between cloth and human body. In this regard, we present DeClotH, which separately reconstructs…

Recently, regression-based methods have dominated the field of 3D human pose and shape estimation. Despite their promising results, a common issue is the misalignment between predictions and image observations, often caused by minor joint…

Learning meaningful and compact representations with disentangled semantic aspects is considered to be of key importance in representation learning. Since real-world data is notoriously costly to collect, many recent state-of-the-art…

Image classification models tend to make decisions based on peripheral attributes of data items that have strong correlation with a target variable (i.e., dataset bias). These biased models suffer from the poor generalization capability…

Modeling the shape of garments has received much attention, but most existing approaches assume the garments to be worn by someone, which constrains the range of shapes they can assume. In this work, we address shape recovery when garments…

Recently, implicit neural representations have gained popularity for learning-based 3D reconstruction. While demonstrating promising results, most implicit approaches are limited to comparably simple geometry of single objects and do not…

Person re identification is a challenging retrieval task that requires matching a person's acquired image across non overlapping camera views. In this paper we propose an effective approach that incorporates both the fine and coarse pose…

Most recent view-invariant action recognition and performance assessment approaches rely on a large amount of annotated 3D skeleton data to extract view-invariant features. However, acquiring 3D skeleton data can be cumbersome, if not…

In this work we address the challenging problem of 3D human pose estimation from single images. Recent approaches learn deep neural networks to regress 3D pose directly from images. One major challenge for such methods, however, is the…

Representation disentanglement aims at learning interpretable features, so that the output can be recovered or manipulated accordingly. While existing works like infoGAN and AC-GAN exist, they choose to derive disjoint attribute code for…

3D face reconstruction from a single image is a challenging problem, especially under partial occlusions and extreme poses. This is because the uncertainty of the estimated 2D landmarks will affect the quality of face reconstruction. In…

We present a novel method for reconstructing clothed humans from a sparse set of, e.g., 1 to 6 RGB images. Despite impressive results from recent works employing deep implicit representation, we revisit the volumetric approach and…

3D reconstruction is a longstanding ill-posed problem, which has been explored for decades by the computer vision, computer graphics, and machine learning communities. Since 2015, image-based 3D reconstruction using convolutional neural…