Skip to content

Computer Vision & Learning Group
  • Home
  • People
  • Publications
  • Research
  • Teaching
  • Open Positions
  • Contact
  • Menu

Research

Current Research Themes​ ​ ​

Image and Video Synthesis: Stable Diffusion, VQGAN, V-UNET, Etc.
Explainable AI
Deep Metric and Representation Learning
Self-Supervised Learning
Behavior Analysis & its Interdisciplinary Applications
Computer Vision in the Digital Humanities

News

Stable Diffusion - Advanced image synthesis for all!
Stable Diffusion in the Press

Open PhD and PostDoc Positions

2024

  • 4 papers accepted at ECCV'24 on:
    • Conditional LoRAs for 0-Shot Control & Altering of T2I-Models
    • ZigMa: Zigzag Mamba Diffusion Model
    • 3D Gaussian Splatting for 3D Stylization using Wasserstein-2 Distance
    • Flow Matching for Boosting Latent Diffusion

    • 2022

  • GCPR'22 Honorable Mention for paper on ArtFID: Quantitative Evaluation of Neural Style Transfer

  • NeurIPS'22 article on retrieval-augmented diffusion models

  • Nature article using image registration to analyze neuropathic pain

  • CVPR'22 tutorial on Deep Visual Similarity and Metric Learning

  • T-PAMI publication accepted on
    • Shared feature learning for Deep Metric Learning (PDF Download)

  • CVPR'22 on latent diffusion models for high-res image synthesis, a.k.a. LDM & Stable Diffusion, source code & models

    • 2021

  • PLOS ONE article on Interactive Retrieval in Art Collections

  • 2 papers accepted at NeurIPS'21 on:
    • Multinomial Diffusion for Improving Autoregressive Image Synthesis
    • Analyzing OOD Generalization in Deep Metric Learning

  • T-PAMI publication accepted on
    • Improving Deep Metric Learning by divide and conquer (PDF Download)

  • Nature Machine Intelligence article on unsupervised behavior analysis & magnification (uBAM) for biomedical diagnostics

  • 3 papers accepted at ICCV'21 on:
    • Transformers for Geometry-Free 3D Novel-View Synthesis
    • iPOKE: Poking a Still Image for Controlled Stochastic Video Synthesis
    • Self-Supervised LiDAR Scene Flow and Motion Segmentation (ORAL)

  • ICML'21 paper accepted on self-distillation for deep metric learning

  • 6 papers accepted at CVPR'21 on:
    • Taming Transformers for Hi-Res Image Synthesis
    • Learning Object Dynamics for Interactive Video Synthesis
    • Stochastic Image-to-Video Synthesis
    • Stroke-based Style Transfer
    • Behavior-driven Synthesis of Human Dynamics
    • Learning Exposure Correction

  • Best Paper Award at CVPR'21—AI for Content Creation WS on
    • High-Res Complex Scene Synthesis with Transformers

  • ICRA'21 paper accepted on 3D object detection

    • 2020

  • NeurIPS'20 ORAL on cINNs for Network-to-Network Translation

  • T-PAMI publication accepted on
    • Shared feature learning for Deep Metric Learning

  • PLoS ONE publication on weakly supervised transliteration alignment for cuneiform sign detection

  • GCPR'20 ORAL on unsupervised part learning by disentangling

  • 2 papers accepted at ECCV'20 on:
    • Explainable AI and semantic image manipulation
    • Deep Metric Learning beyond discriminative features

  • ICML'20 paper accepted on
    • Generalization in Deep Metric Learning

  • Best Paper Award at CVPR'20—AI for Content Creation WS on
    • Interpretable Models for Visual Synthesis

  • 3 papers accepted at CVPR'20 on:
    • Explainable AI
    • Reinforcement Learning for Deep Metric Learning
    • Unsupervised Behavior Analytics

    • 2019

  • 3 papers accepted at ICCV'19

  • Best paper finalist at CVPR'19

  • 3 papers accepted at CVPR'19

    • Categories

    • No categories
    Imprint | Privacy Policy
    A SiteOrigin Theme