Related papers: GIGA: Generalizable Sparse Image-driven Gaussian H…
Creating a high-fidelity, animatable 3D full-body avatar from a single image is a challenging task due to the diverse appearance and poses of humans and the limited availability of high-quality training data. To achieve fast and…
In this paper, we present a novel method that facilitates the creation of vivid 3D Gaussian avatars from monocular video inputs (GVA). Our innovation lies in addressing the intricate challenges of delivering high-fidelity human body…
We present a new approach, termed GPS-Gaussian, for synthesizing novel views of a character in a real-time manner. The proposed method enables 2K-resolution rendering under a sparse-view camera setting. Unlike the original Gaussian…
Sparse volumetric reconstruction and rendering via 3D Gaussian splatting have recently enabled animatable 3D head avatars that are rendered under arbitrary viewpoints with impressive photorealism. Today, such photoreal avatars are seen as a…
Human video generation task has gained significant attention with the advancement of deep generative models. Generating realistic videos with human movements is challenging in nature, due to the intricacies of human body topology and…
While recent advancements in animatable human rendering have achieved remarkable results, they require test-time optimization for each subject which can be a significant limitation for real-world applications. To address this, we tackle the…
Generating lifelike 3D humans from a single RGB image remains a challenging task in computer vision, as it requires accurate modeling of geometry, high-quality texture, and plausible unseen parts. Existing methods typically use multi-view…
Animatable clothing transfer, aiming at dressing and animating garments across characters, is a challenging problem. Most human avatar works entangle the representations of the human body and clothing together, which leads to difficulties…
Image and video synthesis has become a blooming topic in computer vision and machine learning communities along with the developments of deep generative models, due to its great academic and application value. Many researchers have been…
In recent years, diffusion models have revolutionized visual generation, outperforming traditional frameworks like Generative Adversarial Networks (GANs). However, generating images of humans with realistic semantic parts, such as hands and…
We present a new approach for synthesizing novel views of people in new poses. Our novel differentiable renderer enables the synthesis of highly realistic images from any viewpoint. Rather than operating over mesh-based structures, our…
Recent advancements in radiance field rendering show promising results in 3D scene representation, where Gaussian splatting-based techniques emerge as state-of-the-art due to their quality and efficiency. Gaussian splatting is widely used…
Generating animatable human avatars from a single image is essential for various digital human modeling applications. Existing 3D reconstruction methods often struggle to capture fine details in animatable models, while generative…
We introduce Dream, Lift, Animate (DLA), a novel framework that reconstructs animatable 3D human avatars from a single image. This is achieved by leveraging multi-view generation, 3D Gaussian lifting, and pose-aware UV-space mapping of 3D…
Single-image human reconstruction is vital for digital human modeling applications but remains an extremely challenging task. Current approaches rely on generative models to synthesize multi-view images for subsequent 3D reconstruction and…
Human generation has achieved significant progress. Nonetheless, existing methods still struggle to synthesize specific regions such as faces and hands. We argue that the main reason is rooted in the training data. A holistic human dataset…
In this work, we focus on synthesizing high-fidelity novel view images for arbitrary human performers, given a set of sparse multi-view images. It is a challenging task due to the large variation among articulated body poses and heavy…
We propose HeadsUp, a scalable feed-forward method for reconstructing high-quality 3D Gaussian heads from large-scale multi-camera setups. Our method employs an efficient encoder-decoder architecture that compresses input views into a…
The scalability of embodied intelligence is fundamentally constrained by the scarcity of real-world interaction data. While simulation platforms provide a promising alternative, existing approaches often suffer from a substantial visual and…
Creating high-fidelity head avatars from multi-view videos is a core issue for many AR/VR applications. However, existing methods usually struggle to obtain high-quality renderings for all different head components simultaneously since they…