Matthias Nießner

64

Papers

275

Total Citations

Papers (64)

FaceTalk: Audio-Driven Motion Diffusion for Neural Parametric Head Models

Modeling 3D Shapes by Reinforcement Learning

LightIt: Illumination Modeling and Control for Diffusion Models

SceneTex: High-Quality Texture Synthesis for Indoor Scenes via Diffusion Priors

MonoNPHM: Dynamic Head Reconstruction from Monocular Videos

Motion2VecSets: 4D Latent Vector Set Diffusion for Non-rigid Shape Reconstruction and Tracking

GAF: Gaussian Avatar Reconstruction from Monocular Videos via Multi-view Diffusion

QuickSplat: Fast 3D Surface Reconstruction via Learned Gaussian Initialization

Mesh2NeRF: Direct Mesh Supervision for Neural Radiance Field Representation and Generation

LiteReality: Graphic-Ready 3D Scene Reconstruction from RGB-D Scans

SHeaP: Self-supervised Head Geometry Predictor Learned via 2D Gaussians

ViewDiff: 3D-Consistent Image Generation with Text-to-Image Models

Intrinsic Image Diffusion for Indoor Single-view Material Estimation

MultiDiff: Consistent Novel View Synthesis from a Single Image

DiffusionAvatars: Deferred Diffusion for High-fidelity 3D Head Avatars

ScanComplete: Large-Scale Scene Completion and Semantic Segmentation for 3D Scans

StyleMesh: Style Transfer for Indoor 3D Scene Reconstructions

Neural Head Avatars From Monocular RGB Videos

ROCA: Robust CAD Model Retrieval and Alignment From a Single Image

Dense Depth Priors for Neural Radiance Fields From Sparse Input Views

AutoRF: Learning 3D Object Radiance Fields From Single View Observations

Neural RGB-D Surface Reconstruction

Panoptic Lifting for 3D Scene Understanding With Neural Fields

Mask3D: Pre-Training 2D Vision Transformers by Learning Masked 3D Priors

Learning Neural Parametric Head Models

High-Res Facial Appearance Capture From Polarized Smartphone Images

ObjectMatch: Robust Registration Using Canonical Object Correspondences

Learning 3D Scene Priors With 2D Supervision

DiffRF: Rendering-Guided 3D Radiance Field Diffusion

ID-Reveal: Identity-Aware DeepFake Video Detection

Pri3D: Can 3D Priors Help 2D Representation Learning?

4DComplete: Non-Rigid Motion Estimation Beyond the Observable Surface

RetrievalFuse: Neural 3D Scene Reconstruction With a Database

Dynamic Surface Function Networks for Clothed Human Bodies

NPMs: Neural Parametric Models for 3D Deformable Shapes

ScanNet++: A High-Fidelity Dataset of 3D Indoor Scenes

End2End Multi-View Feature Matching with Differentiable Pose Optimization

How to Boost Face Recognition with StyleGAN?

Text2Tex: Text-driven Texture Synthesis via Diffusion Models

CAD-Estate: Large-scale CAD Model Annotation in RGB Videos

Text2Room: Extracting Textured 3D Meshes from 2D Text-to-Image Models

HyperDiffusion: Generating Implicit Neural Fields with Weight-Space Diffusion

UniT3D: A Unified Transformer for 3D Dense Captioning and Visual Grounding

Neural Voice Puppetry: Audio-driven Facial Reenactment

ScanRefer: 3D Object Localization in RGB-D Scans using Natural Language

SceneCAD: Predicting Object Alignments and Layouts in RGB-D Scans

Texturify: Generating Textures on 3D Shape Surfaces

3D Equivariant Graph Implicit Functions

TAFIM: Targeted Adversarial Attacks against Facial Image Manipulations

Pose2Room: Understanding 3D Scenes from Human Activities

RC-MVSNet: Unsupervised Multi-View Stereo with Neural Rendering

D3Net: A Unified Speaker-Listener Architecture for 3D Dense Captioning and Visual Grounding

LT3SD: Latent Trees for 3D Scene Diffusion

4DContrast: Contrastive Learning with Dynamic Correspondences for 3D Scene Understanding

PrEditor3D: Fast and Precise 3D Shape Editing

Zero-shot Inexact CAD Model Alignment from a Single Image

Avat3r: Large Animatable Gaussian Reconstruction Model for High-fidelity 3D Head Avatars

GaussianSpeech: Audio-Driven Personalized 3D Gaussian Avatars

MeshPad: Interactive Sketch-Conditioned Artist-Reminiscent Mesh Generation and Editing

3DGS-LM: Faster Gaussian-Splatting Optimization with Levenberg-Marquardt

GaussianAvatars: Photorealistic Head Avatars with Rigged 3D Gaussians

MeshGPT: Generating Triangle Meshes with Decoder-Only Transformers

DiffuScene: Denoising Diffusion Models for Generative Indoor Scene Synthesis

DPHMs: Diffusion Parametric Head Models for Depth-based Tracking