avatar

Danush Kumar Venkatesh

Ph.D. Student
NCT Dresden & SECAI, TU Dresden, Germany


About Me

I am a final year PhD student at the National Center for Tumor Diseases (NCT) and School of Embedded Composite Artificial Intelligence (SECAI) TU Dresden, Germany under the supervision of Prof. Stefanie Speidel.

I’m currently working on designing generative world models for high-fidelity medical simulation. I develop large-scale synthetic data pipelines for safety-critical applications such as robotic surgery, with a focus on diffusion-based image and video generation.

Beyond pixel-level realism, my goal is to model anatomy, physics, and surgical interaction in a structured, controllable manner to build simulation environments for training both surgeons and robotic systems. By learning generative world models that capture anatomical variability and tool–tissue dynamics over time, I aim to reduce the Sim2Real gap and enable robust, clinically reliable perception and autonomous surgical agents.

Research Interests

  • Generative World Models for Surgery: Learning structured, controllable representations of anatomy and tool–tissue interaction for simulation and training.

  • Image & Video Synthesis: Sim2Real translation, shape- and texture-controlled synthesis, temporally consistent video generation and action-conditioned generation.

  • Embodied AI in Surgery: Simulation-driven training of surgical robots and computer-assisted intervention systems.

News

Publications

  1. SurgFasT: Fast-tracking surgical science with VLMs Challenge
    SurgFasT: Fast-tracking surgical science with VLMs
    Danush Kumar Venkatesh
    Medgemma Impact Challenge, 2026.
    PDF
  2. Mitigating Surgical Data Imbalance with Dual-Prediction Video Diffusion Model arxiv
    Mitigating Surgical Data Imbalance with Dual-Prediction Video Diffusion Model
    Danush Kumar Venkatesh, Adam Schmidt, Muhammad Abdullah Jamal, Omid Mohareri
    Research internship work conducted at Intuitive Surgical, 2025.
    PDF
  3. Towards Application Aligned Synthetic Surgical Image Synthesis NeurIPSw
    Towards Application Aligned Synthetic Surgical Image Synthesis
    Danush Kumar Venkatesh, Stefanie Speidel
    The Thirty-Ninth Annual Conference on Neural Information Processing Systems (NeurIPSw), 2025.
    PDF
  4. Mission Balance - Generating Under-represented Class Samples using Video Diffusion Models MICCAI
    Mission Balance - Generating Under-represented Class Samples using Video Diffusion Models
    Danush Kumar Venkatesh, Isabel Funke, Micha Pfeiffer, Fiona Kolbinger, Hanna Schmeiser, Marius Distler, Jürgen Weitz, Stefanie Speidel
    International Conference on Medical Image Ccomputing & Computer Assisted Intervention (MICCAI), 2025.
    PDF Code Project Page Early accept (top 9%)
  5. Data Augmentation for Surgical Scene Segmentation with Anatomy Aware Diffusion Models WACV
    Data Augmentation for Surgical Scene Segmentation with Anatomy Aware Diffusion Models
    Danush Kumar Venkatesh, Dominik Rivoir, Micha Pfeiffer, Fiona Kolbinger, Stefanie Speidel
    IEEE/CVF Winter Conference on Applications of Computer Vision (WACV), 2025.
    PDF Code Project Page
  6. Generating Surgical Images via Unpaired Image Translation with Latent Consistency Diffusion Models ECCVw
    Generating Surgical Images via Unpaired Image Translation with Latent Consistency Diffusion Models
    Danush Kumar Venkatesh, Dominik Rivoir, Micha Pfeiffer, Stefanie Speidel
    European Conference on Computer Vision workshop (ECCVw), 2024.
    PDF Code
  7. Exploring semantic consistency in unpaired image translation to generate data for surgical applications IPCAI
    Exploring semantic consistency in unpaired image translation to generate data for surgical applications
    Danush Kumar Venkatesh, Dominik Rivoir, Micha Pfeiffer, Fiona Kolbinger, Marius Distler, Jürgen Weitz, Stefanie Speidel
    International Conference on Information Processing in Computer-Assisted Interventions (IPCAI), 2024.
    PDF Code Best Paper Candidate

Services

Conference Reviewers