Matthias Niessner

@UCXN2nYjVT0cR9G61RPEzK5Q - 16.9K subscribers

Welcome to our YouTube channel -- I'm excited to share our newest, cutting-edge research with you! My name is Matthias Niessner and I am a Professor at the Technical University of Munich where I am heading the Visual Computing Lab! I am also a co-founder of synthesia, a brand-new startup working on cutting-edge AI tech for visual effects and movie dubbing. Previously, I was a Visiting Assistant Professor with the MPC-VCC in Pat Hanrahan's group at Stanford University; I received my PhD from the University of Erlangen-Nuremberg under supervision of Guenther Greiner. More information can be found on our group website: www.niessnerlab.org/

Home Videos Live Playlists

OneCanvas: 3D Scene Understanding via Panoramic Reprojection

OneCanvas: 3D Scene Understanding via Panoramic Reprojection Matthias Niessner

1.2K views - 2 weeks ago

GenRecon: Bridging Generative Priors for Multi-View 3D Scene Reconstruction

GenRecon: Bridging Generative Priors for Multi-View 3D Scene Reconstruction Matthias Niessner

2.8K views - 1 month ago

Face Anything: 4D Face Reconstruction from Any Image Sequence

Face Anything: 4D Face Reconstruction from Any Image Sequence Matthias Niessner

1.4K views - 2 months ago

GaussianGPT: Towards Autoregressive 3D Gaussian Scene Generation

GaussianGPT: Towards Autoregressive 3D Gaussian Scene Generation Matthias Niessner

5.1K views - 3 months ago

WorldAgents: Can Foundation Image Models be Agents for 3D World Models?

WorldAgents: Can Foundation Image Models be Agents for 3D World Models? Matthias Niessner

1.1K views - 3 months ago

World Reconstruction from Inconsistent Views

World Reconstruction from Inconsistent Views Matthias Niessner

1.5K views - 3 months ago

Pix2NPHM: Learning to Regress NPHM Reconstructions From a Single Image

Pix2NPHM: Learning to Regress NPHM Reconstructions From a Single Image Matthias Niessner

998 views - 6 months ago

MeshRipple: Structured Autoregressive Generation of Artist-Meshes

MeshRipple: Structured Autoregressive Generation of Artist-Meshes Matthias Niessner

3.1K views - 6 months ago

FlexAvatarLearning Complete 3D Head Avatars with Partial Supervision

FlexAvatarLearning Complete 3D Head Avatars with Partial Supervision Matthias Niessner

1.6K views - 6 months ago

Intrinsic Image Fusion for Multi-View 3D Material Reconstruction

Intrinsic Image Fusion for Multi-View 3D Material Reconstruction Matthias Niessner

601 views - 6 months ago

PercHead: Perceptual Head Model for Single-Image 3D Head Reconstruction & Editing

PercHead: Perceptual Head Model for Single-Image 3D Head Reconstruction & Editing Matthias Niessner

986 views - 8 months ago

WorldExplorer: Towards Generating Fully Navigable 3D Scenes (SIGGRAPH Asia'25)

WorldExplorer: Towards Generating Fully Navigable 3D Scenes (SIGGRAPH Asia'25) Matthias Niessner

1.6K views - 9 months ago

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

LiteReality: Graphics-Ready 3D Scene Reconstruction from RGB-D Scans Matthias Niessner

2.8K views - 1 year ago

BecomingLit: Relightable Gaussian Avatars with Hybrid Neural Shading

BecomingLit: Relightable Gaussian Avatars with Hybrid Neural Shading Matthias Niessner

2.7K views - 1 year ago

PBR-SR: Mesh PBR Texture Super Resolution from 2D Image Priors

PBR-SR: Mesh PBR Texture Super Resolution from 2D Image Priors Matthias Niessner

804 views - 1 year ago

Pixel3DMM: Versatile Screen-Space Priors for Single-Image 3D Face Reconstruction

Pixel3DMM: Versatile Screen-Space Priors for Single-Image 3D Face Reconstruction Matthias Niessner

4.9K views - 1 year ago

LinPrim: Linear Primitives for Differentiable Volumetric Rendering

LinPrim: Linear Primitives for Differentiable Volumetric Rendering Matthias Niessner

1.5K views - 1 year ago

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

SHeaP: Self-Supervised Head Geometry Predictor Learned via 2D Gaussians Matthias Niessner

1.6K views - 1 year ago

IntrinsiX: High-Quality PBR Generation using Image Priors

IntrinsiX: High-Quality PBR Generation using Image Priors Matthias Niessner

1K views - 1 year ago

Animating the Uncaptured: Humanoid Mesh Animation with Video Diffusion Models

Animating the Uncaptured: Humanoid Mesh Animation with Video Diffusion Models Matthias Niessner

1K views - 1 year ago

MeshPad: Interactive Sketch Conditioned Artistic-designed Mesh Generation and Editing

MeshPad: Interactive Sketch Conditioned Artistic-designed Mesh Generation and Editing Matthias Niessner

2.2K views - 1 year ago

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

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

6.8K views - 1 year ago

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

3K views - 1 year ago

PrEditor3D: Fast and Precise 3D Shape Editing

PrEditor3D: Fast and Precise 3D Shape Editing Matthias Niessner

911 views - 1 year ago

GaussianSpeech: Audio-Driven Gaussian Avatars

GaussianSpeech: Audio-Driven Gaussian Avatars Matthias Niessner

2.5K views - 1 year ago

L3DG: Latent 3D Gaussian Diffusion (SIGGRAPH Asia'24)

L3DG: Latent 3D Gaussian Diffusion (SIGGRAPH Asia'24) Matthias Niessner

2K views - 1 year ago

GGHead: Fast and Generalizable 3D Gaussian Heads (SIGGRAPH Asia'24)

GGHead: Fast and Generalizable 3D Gaussian Heads (SIGGRAPH Asia'24) Matthias Niessner

2K views - 1 year ago

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

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

2.4K views - 1 year ago

NPGA: Neural Parametric Gaussian Avatars (SIGGRAPH Asia'24)

NPGA: Neural Parametric Gaussian Avatars (SIGGRAPH Asia'24) Matthias Niessner

3K views - 1 year ago

Mesh2NeRF: Direct Mesh Supervision for Neural Radiance Field Representation and Generation (ECCV'24)

Mesh2NeRF: Direct Mesh Supervision for Neural Radiance Field Representation and Generation (ECCV'24) Matthias Niessner

738 views - 1 year ago

CVPR 2024 Paper Compilation - TUM Visual Computing Lab & Collaborators

CVPR 2024 Paper Compilation - TUM Visual Computing Lab & Collaborators Matthias Niessner

1.4K views - 2 years ago

LightIt: Illumination Modeling and Control for Diffusion Models (CVPR'24)

LightIt: Illumination Modeling and Control for Diffusion Models (CVPR'24) Matthias Niessner

1.6K views - 2 years ago

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

ViewDiff: 3D-Consistent Image Generation with Text-To-Image Models Matthias Niessner

3.8K views - 2 years ago

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

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

1.2K views - 2 years ago

Intrinsic Image Diffusion for Single-view Material Estimation

Intrinsic Image Diffusion for Single-view Material Estimation Matthias Niessner

2.1K views - 2 years ago

PolyDiff: Generating 3D Polygonal Meshes with Diffusion Models

PolyDiff: Generating 3D Polygonal Meshes with Diffusion Models Matthias Niessner

3.6K views - 2 years ago

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

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

3.1K views - 2 years ago

MonoNPHM: Dynamic Head Reconstruction from Monocular Videos

MonoNPHM: Dynamic Head Reconstruction from Monocular Videos Matthias Niessner

3.6K views - 2 years ago

DPHMs: Diffusion Parametric Head Models for Depth-based Tracking

DPHMs: Diffusion Parametric Head Models for Depth-based Tracking Matthias Niessner

1.7K views - 2 years ago

GaussianAvatars: Photorealistic Head Avatars with Rigged 3D Gaussians

GaussianAvatars: Photorealistic Head Avatars with Rigged 3D Gaussians Matthias Niessner

26K views - 2 years ago

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

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

5.7K views - 2 years ago

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

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

3K views - 2 years ago

MeshGPT: Generating Triangle Meshes with Decoder-Only Transformers

MeshGPT: Generating Triangle Meshes with Decoder-Only Transformers Matthias Niessner

48K views - 2 years ago

TriPlaneNet: An Encoder for EG3D Inversion (WACV'24)

TriPlaneNet: An Encoder for EG3D Inversion (WACV'24) Matthias Niessner

1.1K views - 2 years ago

ICCV 2023 Paper Compilation - TUM Visual Computing Lab & Collaborators

ICCV 2023 Paper Compilation - TUM Visual Computing Lab & Collaborators Matthias Niessner

1.6K views - 2 years ago

GANeRF: Leveraging Discriminators to Optimize Neural Radiance Fields (SIGGRAPH Asia'2023)

GANeRF: Leveraging Discriminators to Optimize Neural Radiance Fields (SIGGRAPH Asia'2023) Matthias Niessner

2.6K views - 2 years ago

End2End Multi-View Feature Matching with Differentiable Pose Optimization (ICCV'2023)

End2End Multi-View Feature Matching with Differentiable Pose Optimization (ICCV'2023) Matthias Niessner

2.3K views - 2 years ago

How to Boost Face Recognition with StyleGAN? (ICCV'2023)

How to Boost Face Recognition with StyleGAN? (ICCV'2023) Matthias Niessner

1K views - 2 years ago

SIGGRAPH 2023 Paper Compilation - TUM Visual Computing Lab & Collaborators

SIGGRAPH 2023 Paper Compilation - TUM Visual Computing Lab & Collaborators Matthias Niessner

1.9K views - 2 years ago

HyperDiffusion: Generating Implicit Neural Fields with Weight-Space Diffusion (ICCV'2023)

HyperDiffusion: Generating Implicit Neural Fields with Weight-Space Diffusion (ICCV'2023) Matthias Niessner

5K views - 2 years ago

Text2Room: Extracting Textured 3D Meshes from 2D Text-to-Image Models (ICCV'2023)

Text2Room: Extracting Textured 3D Meshes from 2D Text-to-Image Models (ICCV'2023) Matthias Niessner

8.4K views - 2 years ago

Text2Tex: Text-driven Texture Synthesis via Diffusion Models (ICCV'2023)

Text2Tex: Text-driven Texture Synthesis via Diffusion Models (ICCV'2023) Matthias Niessner

6.9K views - 2 years ago

Introduction to Deep Learning (I2DL 2023) - 5. Scaling Optimization

Introduction to Deep Learning (I2DL 2023) - 5. Scaling Optimization Matthias Niessner

10K views - 2 years ago

Introduction to Deep Learning (I2DL 2023) - 12. Advanced DL Topics

Introduction to Deep Learning (I2DL 2023) - 12. Advanced DL Topics Matthias Niessner

10K views - 2 years ago

Introduction to Deep Learning (I2DL 2023) - 11. RNNs and Transformers

Introduction to Deep Learning (I2DL 2023) - 11. RNNs and Transformers Matthias Niessner

8.5K views - 2 years ago

Introduction to Deep Learning (I2DL 2023) - 10. Architectures

Introduction to Deep Learning (I2DL 2023) - 10. Architectures Matthias Niessner

8.4K views - 2 years ago

Introduction to Deep Learning (I2DL 2023) - 9. Convolutional Neural Networks

Introduction to Deep Learning (I2DL 2023) - 9. Convolutional Neural Networks Matthias Niessner

7.8K views - 2 years ago

Introduction to Deep Learning (I2DL 2023) - 8. Augmentation and Regularization

Introduction to Deep Learning (I2DL 2023) - 8. Augmentation and Regularization Matthias Niessner

7.2K views - 2 years ago

Introduction to Deep Learning (I2DL 2023) - 7. Losses and Activations

Introduction to Deep Learning (I2DL 2023) - 7. Losses and Activations Matthias Niessner

8.2K views - 2 years ago

Introduction to Deep Learning (I2DL 2023) - 6. Training Neural Networks

Introduction to Deep Learning (I2DL 2023) - 6. Training Neural Networks Matthias Niessner

7.4K views - 2 years ago