28Apr2026
Kickoff Keynote
World Models: Connecting the Digital and Physical World
Prof. Dr. Matthias Nießner· TUM 18:00-19:00Boltzmannstraße 3, 85748 Garching, room 02.13.010 LinkedIn post
[02]Meetups
We are organizing events to bring together students, researchers and industry who share our passion for 3D computer vision - no registration needed.
Upcoming Events
No talks scheduled right now - the next series is in the works. Follow us on LinkedIn to hear about it first.
Previous Events30 talks
Summer Semester 2026· 9 talks
05May2026
Professor Talk
Building Interactable 3D Spaces from Imperfect Real-World Data
Prof. Dr. Angela Dai· TUM 18:00-19:00Boltzmannstraße 3, 85748 Garching, room 02.13.010 LinkedIn post
14Jul2026
07Jul2026
> Paper Reading Group
EgoFlow: Gradient-Guided Flow Matching for Egocentric 6DoF Object Motion Generation
30Jun2026
> Paper Reading Group
3D Al for Robot Perception and Learning
09Jun2026
> Paper Reading Group
WorldAgents: Can Foundation Image Models be Agents for 3D World Models?
02Jun2026
> Paper Reading Group
NOV3R: Beyond Pixel-Aligned 3D Reconstruction
26May2026
> Paper Reading Group
GaussianGPT: Towards Autoregressive 3D Gaussian Scene Generation
19May2026
> Paper Reading Group
Vista-SLAM: Efficient and Accurate Real-Time 3D Geometry Recovery
Winter Semester 2025/26· 5 talks
09Dec2025
> Paper Reading Group
Nonisotropic Gaussian Diffusion for Realistic 3D Human Motion Prediction
02Dec2025
> Paper Reading Group
Metric Convolutions: A Unifying Theory to Adaptive Image Convolutions
25Nov2025
> Paper Reading Group
BecomingLit: Relightable Gaussian Avatars with Hybrid Neural Shading
18Nov2025
> Paper Reading Group
IntrinsiX: High-Quality PBR Generation using Image Priors
11Nov2025
> Paper Reading Group
QuickSplat: Fast 3D Surface Reconstruction via Learned Gaussian Initialization
Summer Semester 2025· 7 talks
17Jul2025
> Paper Reading Group
UnScene3D: Unsupervised 3D Instance Segmentation for Indoor Scenes
10Jul2025
> Paper Reading Group
GAF: Gaussian Avatar Reconstruction from Monocular Videos via Multi-view Diffusion
03Jul2025
> Paper Reading Group
PrEditor3D: Fast and Precise 3D Shape Editing
26Jun2025
> Paper Reading Group
DNF: Unconditional 4D Generation with Dictionary-based Neural Fields
12Jun2025
> Paper Reading Group
MeshPad: Interactive Sketch-Conditioned Artist-Designed Mesh Generation and Editing
05Jun2025
> Paper Reading Group
On 3D Virtual Humans and Their Behavior
22May2025
> Paper Reading Group
Visual-inertial tracking for Spatial Agents
Winter Semester 2024/25· 9 talks
06Feb2025
> Paper Reading Group
One-Shot Head Reconstruction Model with Virtual Views
30Jan2025
> Paper Reading Group
Power Variable Projection for Initialization-Free Large-Scale Bundle Adjustment
12Dec2024
> Paper Reading Group
MeshArt: Generating Articulated Meshes with Structure-guided Transformers
05Dec2024
> Paper Reading Group
GaussianSpeech: Audio-Driven Gaussian Avatars
28Nov2024
21Nov2024
> Paper Reading Group
Coherent 3D Scene Diffusion From a Single RGB Image
31Oct2024
> Paper Reading Group
NPHM: Learning Neural Parametric Head Models
24Oct2024
> Paper Reading Group
Text2Room: Extracting Textured 3D Meshes from 2D Text-to-Image Models
17Oct2024
> Paper Reading Group