# Video Self-Distillation for Single-Image Encoders: A Step Toward Physically Plausible Perception

Source: [Video Self-Distillation for Single-Image Encoders: A Step Toward Physically Plausible Perception](<https://www.sota2.com/research/paper/68fa7a391e209131cea81ea7>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2025-10-26T05:15:13.470Z

Authors: Marcel Simon, Tae-Ho Kim, Seul-Ki Yeom

Published: 2025-07-25T13:52:31.000Z

## Abstract

Self-supervised image encoders such as DINO have recently gained significant interest for learning robust visual features without labels. However, most SSL methods train on static images and miss the temporal cues inherent in videos. We introduce a video-distilled single-image encoder trained to predict the next-frame representation from the current frame. This simple objective injects 3D spatial and temporal priors without optical flow or tracking. When pre-training on a single 2-hour video, our approach raises the mean Intersection-over-Union (mIoU) on ADE20K from 35.0 (DoRA) to 36.4 while remaining a drop-in replacement for image-only pipelines. Our results highlight video self-distillation as a lightweight route to geometry-aware perception an essential ingredient for physically plausible world models and Physical AI.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/2507.19272>)

[PDF](<https://arxiv.org/pdf/2507.19272.pdf>)