# Mission Balance: Generating Under-represented Class Samples using Video Diffusion Models

arXiv: https://arxiv.org/abs/2505.09858 · HTML: https://mlsanity.com/paper/2505.09858/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Placed in Medical imaging and segmentation, one of 14 directions in Diffusion models.
- Builds on 25 of its 30 references that are in the map.
- First posted on arXiv 14 May 2025.

## Placed in

- Diffusion models / [Medical imaging and segmentation](https://mlsanity.com/diffusion/medical-imaging-and-segmentation/)

## Builds on (most cited first, 25 of 25)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [U-Net: Convolutional Networks for Biomedical Image Segmentation](https://mlsanity.com/paper/1505.04597/) (2015)
- [High-Resolution Image Synthesis with Latent Diffusion Models](https://mlsanity.com/paper/2112.10752/) (2021)
- [Diffusion Models Beat GANs on Image Synthesis](https://mlsanity.com/paper/2105.05233/) (2021)
- [Adding Conditional Control to Text-to-Image Diffusion Models](https://mlsanity.com/paper/2302.05543/) (2023)
- [Video Diffusion Models](https://mlsanity.com/paper/2204.03458/) (2022)
- [Align your Latents: High-Resolution Video Synthesis with Latent Diffusion Models](https://mlsanity.com/paper/2304.08818/) (2023)
- [AnimateDiff: Animate Your Personalized Text-to-Image Diffusion Models without Specific Tuning](https://mlsanity.com/paper/2307.04725/) (2023)
- [X3D: Expanding Architectures for Efficient Video Recognition](https://mlsanity.com/paper/2004.04730/) (2020)
- [Can Spatiotemporal 3D CNNs Retrace the History of 2D CNNs and ImageNet?](https://mlsanity.com/paper/1711.09577/) (2017)
- [Reliable Fidelity and Diversity Metrics for Generative Models](https://mlsanity.com/paper/2002.09797/) (2020)
- [Latent Video Diffusion Models for High-Fidelity Long Video Generation](https://mlsanity.com/paper/2211.13221/) (2022)
- [Synthetic Data from Diffusion Models Improves ImageNet Classification](https://mlsanity.com/paper/2304.08466/) (2023)
- [Rethinking FID: Towards a Better Evaluation Metric for Image Generation](https://mlsanity.com/paper/2401.09603/) (2023)
- [How Faithful is your Synthetic Data? Sample-level Metrics for Evaluating and Auditing Generative Models](https://mlsanity.com/paper/2102.08921/) (2021)
- [Surgical Data Science -- from Concepts toward Clinical Translation](https://mlsanity.com/paper/2011.02284/) (2020)
- [SAR-RARP50: Segmentation of surgical instrumentation and Action Recognition on Robot-Assisted Radical Prostatectomy Challenge](https://mlsanity.com/paper/2401.00496/) (2023)
- [Endora: Video Generation Models as Endoscopy Simulators](https://mlsanity.com/paper/2403.11050/) (2024)
- [SurGen: Text-Guided Diffusion Model for Surgical Video Generation](https://mlsanity.com/paper/2408.14028/) (2024)
- [Synthesising Rare Cataract Surgery Samples with Guided Diffusion Models](https://mlsanity.com/paper/2308.02587/) (2023)
- [Exploring Semantic Consistency in Unpaired Image Translation to Generate Data for Surgical Applications](https://mlsanity.com/paper/2309.03048/) (2023)
- [Interactive Generation of Laparoscopic Videos with Diffusion Models](https://mlsanity.com/paper/2406.06537/) (2024)
- [Data Augmentation for Surgical Scene Segmentation with Anatomy-Aware Diffusion Models](https://mlsanity.com/paper/2410.07753/) (2024)
- [SimuScope: Realistic Endoscopic Synthetic Dataset Generation through Surgical Simulation and Diffusion Models](https://mlsanity.com/paper/2412.02332/) (2024)

## Built on by (most cited first, 1 of 1)

- [Mitigating Surgical Data Imbalance with Dual-Prediction Video Diffusion Model](https://mlsanity.com/paper/2510.07345/) (2025)

## Abstract (arXiv)

Computer-assisted interventions can improve intra-operative guidance, particularly through deep learning methods that harness the spatiotemporal information in surgical videos. However, the severe data imbalance often found in surgical video datasets hinders the development of high-performing models. In this work, we aim to overcome the data imbalance by synthesizing surgical videos. We propose a unique two-stage, text-conditioned diffusion-based method to generate high-fidelity surgical videos for under-represented classes. Our approach conditions the generation process on text prompts and decouples spatial and temporal modeling by utilizing a 2D latent diffusion model to capture spatial content and then integrating temporal attention layers to ensure temporal consistency. Furthermore, we introduce a rejection sampling strategy to select the most suitable synthetic samples, effectively augmenting existing datasets to address class imbalance. We evaluate our method on two downstream tasks-surgical action recognition and intra-operative event prediction-demonstrating that incorporating synthetic videos from our approach substantially enhances model performance. We open-source our implementation at https://gitlab.com/nct_tso_public/surgvgen.