6 papers
QuickSplat: Fast 3D Surface Reconstruction via Learned Gaussian Initialization
Yueh-Cheng Liu, Lukas Höllein, Matthias NieÃner +1
Surface reconstruction is fundamental to computer vision and graphics, enabling applications in 3D modeling, mixed reality, robotics, and more. Existing approaches based on volumet…
Animating the Uncaptured: Humanoid Mesh Animation with Video Diffusion Models
Marc Benedà San Millán, Angela Dai, Matthias NieÃner
Animation of humanoid characters is essential in various graphics applications, but requires significant time and cost to create realistic animations. We propose an approach to syn…
Coherent 3D Scene Diffusion From a Single RGB Image
Manuel Dahnert, Angela Dai, Norman Müller +1
We present a novel diffusion-based approach for coherent 3D scene reconstruction from a single RGB image. Our method utilizes an image-conditioned 3D scene diffusion model to simul…
PrEditor3D: Fast and Precise 3D Shape Editing
Ziya Erkoç, Can Gümeli, Chaoyang Wang +5
We propose a training-free approach to 3D editing that enables the editing of a single shape within a few minutes. The edited 3D mesh aligns well with the prompts, and remains iden…
GaussianSpeech: Audio-Driven Gaussian Avatars
Shivangi Aneja, Artem Sevastopolsky, Tobias Kirschstein +3
We introduce GaussianSpeech, a novel approach that synthesizes high-fidelity animation sequences of photo-realistic, personalized 3D human head avatars from spoken audio. To captur…
L3DG: Latent 3D Gaussian Diffusion
Barbara Roessle, Norman Müller, Lorenzo Porzi +4
We propose L3DG, the first approach for generative 3D modeling of 3D Gaussians through a latent 3D Gaussian diffusion formulation. This enables effective generative 3D modeling, sc…