Marcel C. Bühler
YOU?
Author Swipe
View article: Dream, Lift, Animate: From Single Images to Animatable Gaussian Avatars
Dream, Lift, Animate: From Single Images to Animatable Gaussian Avatars Open
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 …
View article: HyperGaussians: High-Dimensional Gaussian Splatting for High-Fidelity Animatable Face Avatars
HyperGaussians: High-Dimensional Gaussian Splatting for High-Fidelity Animatable Face Avatars Open
We introduce HyperGaussians, a novel extension of 3D Gaussian Splatting for high-quality animatable face avatars. Creating such detailed face avatars from videos is a challenging problem and has numerous applications in augmented and virtu…
View article: Cafca: High-quality Novel View Synthesis of Expressive Faces from Casual Few-shot Captures
Cafca: High-quality Novel View Synthesis of Expressive Faces from Casual Few-shot Captures Open
Volumetric modeling and neural radiance field representations have revolutionized 3D face capture and photorealistic novel view synthesis. However, these methods often require hundreds of multi-view input images and are thus inapplicable t…
View article: SurFhead: Affine Rig Blending for Geometrically Accurate 2D Gaussian Surfel Head Avatars
SurFhead: Affine Rig Blending for Geometrically Accurate 2D Gaussian Surfel Head Avatars Open
Recent advancements in head avatar rendering using Gaussian primitives have achieved significantly high-fidelity results. Although precise head geometry is crucial for applications like mesh reconstruction and relighting, current methods s…
View article: MagicMirror: Fast and High-Quality Avatar Generation with a Constrained Search Space
MagicMirror: Fast and High-Quality Avatar Generation with a Constrained Search Space Open
We introduce a novel framework for 3D human avatar generation and personalization, leveraging text prompts to enhance user engagement and customization. Central to our approach are key innovations aimed at overcoming the challenges in phot…
View article: Preface: A Data-driven Volumetric Prior for Few-shot Ultra High-resolution Face Synthesis
Preface: A Data-driven Volumetric Prior for Few-shot Ultra High-resolution Face Synthesis Open
NeRFs have enabled highly realistic synthesis of human faces including complex appearance and reflectance effects of hair and skin. These methods typically require a large number of multi-view input images, making the process hardware inte…
View article: I M Avatar: Implicit Morphable Head Avatars from Videos
I M Avatar: Implicit Morphable Head Avatars from Videos Open
Traditional 3D morphable face models (3DMMs) provide fine-grained control over expression but cannot easily capture geometric and appearance details. Neural volumetric representations approach photorealism but are hard to animate and do no…
View article: VariTex: Variational Neural Face Textures
VariTex: Variational Neural Face Textures Open
Deep generative models can synthesize photorealistic images of human faces with novel identities. However, a key challenge to the wide applicability of such techniques is to provide independent control over semantically meaningful paramete…
View article: VariTex: Variational Neural Face Textures
VariTex: Variational Neural Face Textures Open
Deep generative models can synthesize photorealistic images of human faces with novel identities. However, a key challenge to the wide applicability of such techniques is to provide independent control over semantically meaningful paramete…
View article: DeepSEE: Deep Disentangled Semantic Explorative Extreme Super-Resolution
DeepSEE: Deep Disentangled Semantic Explorative Extreme Super-Resolution Open
Super-resolution (SR) is by definition ill-posed. There are infinitely many plausible high-resolution variants for a given low-resolution natural image. Most of the current literature aims at a single deterministic solution of either high …
View article: Content-Consistent Generation of Realistic Eyes with Style
Content-Consistent Generation of Realistic Eyes with Style Open
Accurately labeled real-world training data can be scarce, and hence recent works adapt, modify or generate images to boost target datasets. However, retaining relevant details from input data in the generated images is challenging and fai…