Related papers: Creating and Reenacting Controllable 3D Humans wit…
We introduce a new method that generates photo-realistic humans under novel views and poses given a monocular video as input. Despite the significant progress recently on this topic, with several methods exploring shared canonical neural…
Human-centric volumetric videos offer immersive free-viewpoint experiences, yet existing methods focus either on replaying general dynamic scenes or animating human avatars, limiting their ability to re-perform general dynamic scenes. In…
We present a novel method to learn temporally consistent 3D reconstruction of clothed people from a monocular video. Recent methods for 3D human reconstruction from monocular video using volumetric, implicit or parametric human shape…
This paper presents a novel framework to recover detailed human body shapes from a single image. It is a challenging task due to factors such as variations in human shapes, body poses, and viewpoints. Prior methods typically attempt to…
Animating human face images aims to synthesize a desired source identity in a natural-looking way mimicking a driving video's facial movements. In this context, Generative Adversarial Networks have demonstrated remarkable potential in…
The latest developments in 3D capturing, processing, and rendering provide means to unlock novel 3D application pathways. The main elements of an integrated platform, which target tele-immersion and future 3D applications, are described in…
3D representation and reconstruction of human bodies have been studied for a long time in computer vision. Traditional methods rely mostly on parametric statistical linear models, limiting the space of possible bodies to linear…
Reconstruction of the shape and motion of humans from RGB-D is a challenging problem, receiving much attention in recent years. Recent approaches for full-body reconstruction use a statistic shape model, which is built upon accurate…
We present a novel pipeline for learning high-quality triangular human avatars from multi-view videos. Recent methods for avatar learning are typically based on neural radiance fields (NeRF), which is not compatible with traditional…
This paper introduces a novel approach to monocular 3D human pose estimation using contextualized representation learning with the Transformer-GCN dual-stream model. Monocular 3D human pose estimation is challenged by depth ambiguity,…
Creating high-quality controllable 3D human models from multi-view RGB videos poses a significant challenge. Neural radiance fields (NeRFs) have demonstrated remarkable quality in reconstructing and free-viewpoint rendering of static as…
Augmented reality applications have rapidly spread across online platforms, allowing consumers to virtually try-on a variety of products, such as makeup, hair dying, or shoes. However, parametrizing a renderer to synthesize realistic images…
Generating and representing human behavior are of major importance for various computer vision applications. Commonly, human video synthesis represents behavior as sequences of postures while directly predicting their likely progressions or…
In recent years, the role of image generative models in facial reenactment has been steadily increasing. Such models are usually subject-agnostic and trained on domain-wide datasets. The appearance of the reenacted individual is learned…
Combining the signed distance function (SDF) and differentiable volume rendering has emerged as a powerful paradigm for surface reconstruction from multi-view images without 3D supervision. However, current methods are impeded by requiring…
We propose Neural Actor (NA), a new method for high-quality synthesis of humans from arbitrary viewpoints and under arbitrary controllable poses. Our method is built upon recent neural scene representation and rendering works which learn…
Recent advances in generative models have achieved high-fidelity in 3D human reconstruction, yet their utility for specific tasks (e.g., human 3D segmentation) remains constrained. We propose HumanCrafter, a unified framework that enables…
We propose SelfRecon, a clothed human body reconstruction method that combines implicit and explicit representations to recover space-time coherent geometries from a monocular self-rotating human video. Explicit methods require a predefined…
Achieving fine-grained controllability in human image synthesis is a long-standing challenge in computer vision. Existing methods primarily focus on either facial synthesis or near-frontal body generation, with limited ability to…
Human motion modelling is a classical problem at the intersection of graphics and computer vision, with applications spanning human-computer interaction, motion synthesis, and motion prediction for virtual and augmented reality. Following…