# Improving Semantic Segmentation through Spatio-Temporal Consistency Learned from Videos

Source: [Improving Semantic Segmentation through Spatio-Temporal Consistency Learned from Videos](<https://www.sota2.com/research/paper/68fa67961e209131cea173dc>)

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

Data updated: 2025-10-25T22:18:12.808Z

Authors: Ankita Pasad, Ariel Gordon, Tsung-Yi Lin, Anelia Angelova

Published: 2020-04-11T07:09:29.000Z

## Abstract

We leverage unsupervised learning of depth, egomotion, and camera intrinsics to improve the performance of single-image semantic segmentation, by enforcing 3D-geometric and temporal consistency of segmentation masks across video frames. The predicted depth, egomotion, and camera intrinsics are used to provide an additional supervision signal to the segmentation model, significantly enhancing its quality, or, alternatively, reducing the number of labels the segmentation model needs. Our experiments were performed on the ScanNet dataset.

## 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/2004.05324>)

[PDF](<https://arxiv.org/pdf/2004.05324.pdf>)