Danush Kumar Venkatesh

About Me

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

My research focuses on developing large-scale synthetic training data for critical biomedical applications, such as robotic surgery. I’ve focussed mainly on diffusion models, to create training datasets that feature anatomically accurate structures and high fidelity textures. My goal is to significantly minimize the Sim2Real domain gap, accelerating the development of robust computer vision systems and embodied agents for real-world clinical impact.

Research Interests

Image synthesis: Sim2Real translation, Shape & texture controlled synthesis
Video generation: Temporal consistency, Kinematic & action conditioned generation

News

[Oct. 2025] The work on video diffusion models from the internship at Intuitive Surgical is published in arxiv.
[Aug. 2025] Our paper on application alignment of diffusion models is accepted at NeurIPSw 2025.
[May. 2025] Our paper about video diffusion is early accepted at MICCAI 2025.
[Mar. 2025] I’m starting as a PhD Intern at Intuitive Surgical (US).
[Nov. 2024] Our paper about anatomy aware diffusion is accepted to WACV 2025.
[Aug. 2024] Our paper about image synthesis with diffusion is accepted to ECCVw 2024.
[Jun. 2024] I won the Best Poster Award at EEML summer school.
[Apr. 2024] I got accepted to EEML summer school organised by Google Deepmind.
[Jan. 2024] Our paper on semantic consistent image generation is accepted to IPCAI 2024.
[Jun. 2023] I will be attending the Generative Modeling Summer School (GeMSS).

Publications

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

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

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%)

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

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

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

About Me

Research Interests

News

Publications

Services

Conference Reviewers