Marvin Seyfarth
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Research Interests
Marvin Seyfarth has a total of 4 co-authors. Here are the top co-authors by number of shared publications:
- Salman Ul Hassan Dar
Department of Electrical and Electronics Engineering, Bilkent University, Ankara 06800, Turkey; National Magnetic Resonance Research Center (UMRAM), Bilkent University, Ankara 06800, Turkey
2 shared publications - Sandy Engelhardt
Heidelberg University Hospital
2 shared publications Salman Ul Hassan Dar
Department of Internal Medicine III Heidelberg University Hospital Germany
1 shared publicationSandy Engelhardt
Department of Internal Medicine III Heidelberg University Hospital Germany
1 shared publication
Latest Publications
- 12 March 2026
- Published by Springer Nature
- p. 420-426
Rethinking Diversity Metrics in Medical Imaging with Wasserstein Distance
- 12 March 2026
- Published by Springer Nature
- p. 420-426
Rethinking Diversity Metrics in Medical Imaging with Wasserstein Distance
- 6 October 2024
- Published by Springer Nature
- p. 146-156
Latent Pollution Model: The Hidden Carbon Footprint in 3D Image Synthesis
- 6 October 2024
- Published by Springer Nature
- p. 146-156
Latent Pollution Model: The Hidden Carbon Footprint in 3D Image Synthesis
- Open Access
Latent Pollution Model: The Hidden Carbon Footprint in 3D Image Synthesis
Contemporary developments in generative AI are rapidly transforming the field of medical AI. These developments have been predominantly driven by the availability of large datasets and high computing power, which have facilitated a significant increase in model capacity. Despite their considerable potential, these models demand substantially high power, leading to high carbon dioxide (CO2) emissions. Given the harm such models are causing to the environment, there has been little focus on the carbon footprints of such models. This study analyzes carbon emissions from 2D and 3D latent diffusion models (LDMs) during training and data generation phases, revealing a surprising finding: the synthesis of large images contributes most significantly to these emissions. We assess different scenarios including model sizes, image dimensions, distributed training, and data generation steps. Our findings reveal substantial carbon emissions from these models, with training 2D and 3D models comparable to driving a car for 10 km and 90 km, respectively. The process of data generation is even more significant, with CO2 emissions equivalent to driving 160 km for 2D models and driving for up to 3345 km for 3D synthesis. Additionally, we found that the location of the experiment can increase carbon emissions by up to 94 times, and even the time of year can influence emissions by up to 50%. These figures are alarming, considering they represent only a single training and data generation phase for each model. Our results emphasize the urgent need for developing environmentally sustainable strategies in generative AI.
Open AccessLatent Pollution Model: The Hidden Carbon Footprint in 3D Image Synthesis
Contemporary developments in generative AI are rapidly transforming the field of medical AI. These developments have been predominantly driven by the availability of large datasets and high computing power, which have facilitated a significant increase in model capacity. Despite their considerable potential, these models demand substantially high power, leading to high carbon dioxide (CO2) emissions. Given the harm such models are causing to the environment, there has been little focus on the carbon footprints of such models. This study analyzes carbon emissions from 2D and 3D latent diffusion models (LDMs) during training and data generation phases, revealing a surprising finding: the synthesis of large images contributes most significantly to these emissions. We assess different scenarios including model sizes, image dimensions, distributed training, and data generation steps. Our findings reveal substantial carbon emissions from these models, with training 2D and 3D models comparable to driving a car for 10 km and 90 km, respectively. The process of data generation is even more significant, with CO2 emissions equivalent to driving 160 km for 2D models and driving for up to 3345 km for 3D synthesis. Additionally, we found that the location of the experiment can increase carbon emissions by up to 94 times, and even the time of year can influence emissions by up to 50%. These figures are alarming, considering they represent only a single training and data generation phase for each model. Our results emphasize the urgent need for developing environmentally sustainable strategies in generative AI.