Matthias Niessner

16.8K subscribers

216 videos

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 T...

Latest Videos

Face Anything 4D Face Reconstruction from Any Image Sequence

GaussianGPT Towards Autoregressive 3D Gaussian Scene Generation

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

World Reconstruction from Inconsistent Views

Pix2NPHM Learning to Regress NPHM Reconstructions From a Single Image

MeshRipple Structured Autoregressive Generation of Artist-Meshes

FlexAvatarLearning Complete 3D Head Avatars with Partial Supervision

Intrinsic Image Fusion for Multi-View 3D Material Reconstruction

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

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

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

BecomingLit Relightable Gaussian Avatars with Hybrid Neural Shading

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

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

LinPrim Linear Primitives for Differentiable Volumetric Rendering

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

IntrinsiX High-Quality PBR Generation using Image Priors

Animating the Uncaptured Humanoid Mesh Animation with Video Diffusion Models

MeshPad Interactive Sketch Conditioned Artistic-designed Mesh Generation and Editing

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

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

PrEditor3D Fast and Precise 3D Shape Editing

GaussianSpeech Audio-Driven Gaussian Avatars

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

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

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

NPGA Neural Parametric Gaussian Avatars (SIGGRAPH Asia'24)

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

CVPR 2024 Paper Compilation - TUM Visual Computing Lab & Collaborators

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