Selective video unlearning removes concepts while preserving the scene
FOMO: Forget the Concept, Don't Miss Out on the Scene in Selective Video Unlearning
Computer Vision and Pattern Recognition
Summary
Videos created by AI can sometimes include unwanted objects, identities, or even unsafe content. The authors developed a method called FOMO that removes just the unwanted parts from videos without messing up the rest of the scene. Unlike previous methods, FOMO also works by removing certain movements or actions in videos. This means it can keep the background and overall look mostly unchanged while erasing only the target content.
What this means in practice
- •For video editors: Remove undesirable objects or motions from videos automatically while keeping the rest of the scene intact.
- •For content moderators: Filter out unsafe or harmful video content by selectively eliminating problematic parts without altering the entire video.
Authors
Łukasz Rudnik, Agnieszka Polowczyk, Alicja Polowczyk, Przemysław Spurek
Abstract
The rapid advancement of generative video models has enabled the synthesis of increasingly realistic and temporally coherent videos, while also raising concerns about the generation of harmful content. The reliance on large-scale web datasets during training inevitably exposes these models to undesirable material, making concept unlearning an essential mitigation. Existing methods mainly target static visual concepts, such as objects, identities, or unsafe appearance, largely overlooking motion unlearning. Furthermore, these approaches often pay little attention to preserving the surrounding scene. As a result, successful concept removal may unintentionally alter the background, composition, or overall video dynamics. We argue that effective unlearning should ideally change only what is targeted, while minimizing unnecessary changes to the remaining scene. In this work, we introduce FOMO, to the best of our knowledge the first training-based selective video unlearning method that directly treats preservation of the original scene as a priority. We formulate unlearning around two complementary objectives: what to change and what to preserve. Our method localizes concept-related representations and modifies them, while the preservation mechanism maintains non-target scene information without requiring auxiliary data. Beyond simply erasing unwanted concepts, FOMO explicitly redirects the generation toward a specified safe alternative. We further extend this formulation to motion unlearning, where the concept is defined by temporal behavior rather than a fixed spatial region. Our solution achieves effective unlearning across unsafe content, object, and motion concepts, while achieving the best trade-off between concept removal and scene preservation. Code: https://github.com/gmum/FOMO Project Page https://gmum.github.io/FOMO