526 citations · 1.4k across the 51 of their papers we have counts for
61 papers
QuickSplat: Fast 3D Surface Reconstruction via Learned Gaussian Initialization
Yueh-Cheng Liu, Lukas Höllein, Matthias Nießner +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 Benedí San Millán, Angela Dai, Matthias Nießner
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…
FaceTalk: Audio-Driven Motion Diffusion for Neural Parametric Head Models
Shivangi Aneja, Justus Thies, Angela Dai +1
We introduce FaceTalk, a novel generative approach designed for synthesizing high-fidelity 3D motion sequences of talking human heads from input audio signal. To capture the expres…
DPHMs: Diffusion Parametric Head Models for Depth-based Tracking
Jiapeng Tang, Angela Dai, Yinyu Nie +3
We introduce Diffusion Parametric Head Models (DPHMs), a generative model that enables robust volumetric head reconstruction and tracking from monocular depth sequences. While rece…
MeshGPT: Generating Triangle Meshes with Decoder-Only Transformers
Yawar Siddiqui, Antonio Alliegro, Alexey Artemov +5
We introduce MeshGPT, a new approach for generating triangle meshes that reflects the compactness typical of artist-created meshes, in contrast to dense triangle meshes extracted b…
ScanNet++: A High-Fidelity Dataset of 3D Indoor Scenes
Chandan Yeshwanth, Yueh-Cheng Liu, Matthias Nießner +1
We present ScanNet++, a large-scale dataset that couples together capture of high-quality and commodity-level geometry and color of indoor scenes. Each scene is captured with a hig…
Mesh2Tex: Generating Mesh Textures from Image Queries
Alexey Bokhovkin, Shubham Tulsiani, Angela Dai
Remarkable advances have been achieved recently in learning neural representations that characterize object geometry, while generating textured objects suitable for downstream appl…
HyperDiffusion: Generating Implicit Neural Fields with Weight-Space Diffusion
Ziya Erkoç, Fangchang Ma, Qi Shan +2
Implicit neural fields, typically encoded by a multilayer perceptron (MLP) that maps from coordinates (e.g., xyz) to signals (e.g., signed distances), have shown remarkable promise…
UnScene3D: Unsupervised 3D Instance Segmentation for Indoor Scenes
David Rozenberszki, Or Litany, Angela Dai
3D instance segmentation is fundamental to geometric understanding of the world around us. Existing methods for instance segmentation of 3D scenes rely on supervision from expensiv…
DiffuScene: Denoising Diffusion Models for Generative Indoor Scene Synthesis
Jiapeng Tang, Yinyu Nie, Lev Markhasin +3
We present DiffuScene for indoor 3D scene synthesis based on a novel scene configuration denoising diffusion model. It generates 3D instance properties stored in an unordered objec…
Mask3D: Pre-training 2D Vision Transformers by Learning Masked 3D Priors
Ji Hou, Xiaoliang Dai, Zijian He +2
Current popular backbones in computer vision, such as Vision Transformers (ViT) and ResNets are trained to perceive the world from 2D images. However, to more effectively understan…
Panoptic Lifting for 3D Scene Understanding with Neural Fields
Yawar Siddiqui, Lorenzo Porzi, Samuel Rota Buló +4
We propose Panoptic Lifting, a novel approach for learning panoptic 3D volumetric representations from images of in-the-wild scenes. Once trained, our model can render color images…
ObjectMatch: Robust Registration using Canonical Object Correspondences
Can Gümeli, Angela Dai, Matthias Nießner
We present ObjectMatch, a semantic and object-centric camera pose estimator for RGB-D SLAM pipelines. Modern camera pose estimators rely on direct correspondences of overlapping re…
ClipFace: Text-guided Editing of Textured 3D Morphable Models
Shivangi Aneja, Justus Thies, Angela Dai +1
We propose ClipFace, a novel self-supervised approach for text-guided editing of textured 3D morphable model of faces. Specifically, we employ user-friendly language prompts to ena…
Neural Poisson: Indicator Functions for Neural Fields
Angela Dai, Matthias Nießner
Implicit neural field generating signed distance field representations (SDFs) of 3D shapes have shown remarkable progress in 3D shape reconstruction and generation. We introduce a…
Learning 3D Scene Priors with 2D Supervision
Yinyu Nie, Angela Dai, Xiaoguang Han +1
Holistic 3D scene understanding entails estimation of both layout configuration and object geometry in a 3D environment. Recent works have shown advances in 3D scene estimation fro…
FutureHuman3D: Forecasting Complex Long-Term 3D Human Behavior from Video Observations
Christian Diller, Thomas Funkhouser, Angela Dai
We present a generative approach to forecast long-term future human behavior in 3D, requiring only weak supervision from readily available 2D human action data. This is a fundament…
PatchComplete: Learning Multi-Resolution Patch Priors for 3D Shape Completion on Unseen Categories
Yuchen Rao, Yinyu Nie, Angela Dai
While 3D shape representations enable powerful reasoning in many visual and perception applications, learning 3D shape priors tends to be constrained to the specific categories tra…
Texturify: Generating Textures on 3D Shape Surfaces
Yawar Siddiqui, Justus Thies, Fangchang Ma +3
Texture cues on 3D objects are key to compelling visual representations, with the possibility to create high visual fidelity with inherent spatial consistency across different view…
Language-Grounded Indoor 3D Semantic Segmentation in the Wild
David Rozenberszki, Or Litany, Angela Dai
Recent advances in 3D semantic segmentation with deep neural networks have shown remarkable success, with rapid performance increase on available datasets. However, current 3D sema…