activity
20232026
most citedSynthesising Rare Cataract Surgery Samples with Guided Diffusion Models

13 citations · 25 across the 9 of their papers we have counts for

collaborators
Showing cs.CVShow all

6 papers · 1 filter

cs.CV2026

SWoMo: Neuro-Symbolic World Model for Cataract Surgery Simulation

Ssharvien Kumar Sivakumar, Akwele Johnson, Anirudh Dhingra +3

Realistic surgical simulation plays a crucial role in training novice surgeons and in the development of autonomous agents. World models can scale such simulation environments to r…

cs.CV2026

VolDiT: Controllable Volumetric Medical Image Synthesis with Diffusion Transformers

Marvin Seyfarth, Salman Ul Hassan Dar, Yannik Frisch +4

Diffusion models have become a leading approach for high-fidelity medical image synthesis. However, most existing methods for 3D medical image generation rely on convolutional U-Ne…

cs.CV2025

SG2VID: Scene Graphs Enable Fine-Grained Control for Video Synthesis

Ssharvien Kumar Sivakumar, Yannik Frisch, Ghazal Ghazaei +1

Surgical simulation plays a pivotal role in training novice surgeons, accelerating their learning curve and reducing intra-operative errors. However, conventional simulation tools…

cs.CV2025★ 3 cited

SurGrID: Controllable Surgical Simulation via Scene Graph to Image Diffusion

Yannik Frisch, Ssharvien Kumar Sivakumar, Çağhan Köksal +5

Surgical simulation offers a promising addition to conventional surgical training. However, available simulation tools lack photorealism and rely on hardcoded behaviour. Denoising…

cs.CV2025★ 1 cited

GAUDA: Generative Adaptive Uncertainty-guided Diffusion-based Augmentation for Surgical Segmentation

Yannik Frisch, Christina Bornberg, Moritz Fuchs +1

Augmentation by generative modelling yields a promising alternative to the accumulation of surgical data, where ethical, organisational and regulatory aspects must be considered. Y…

cs.CV2024★ 1 cited

Frequency-Time Diffusion with Neural Cellular Automata

John Kalkhof, Arlene Kühn, Yannik Frisch +1

Despite considerable success, large Denoising Diffusion Models (DDMs) with UNet backbone pose practical challenges, particularly on limited hardware and in processing gigapixel ima…