# Casting Geometric Constraints in Semantic Segmentation as Semi-Supervised Learning

## TL;DR

This paper introduces a semi-supervised learning approach that leverages geometric constraints to improve indoor scene segmentation across different datasets and video frames, addressing dataset bias.

## Contribution

It demonstrates that geometric constraints can be integrated as semi-supervised terms, enabling effective cross-dataset and video-based segmentation with limited annotations.

## Key findings

- Effective segmentation of new indoor scenes from video frames.
- Utilizes geometric constraints as semi-supervised learning terms.
- Achieves accurate segmentation with limited annotations.

## Abstract

We propose a simple yet effective method to learn to segment new indoor scenes from video frames: State-of-the-art methods trained on one dataset, even as large as the SUNRGB-D dataset, can perform poorly when applied to images that are not part of the dataset, because of the dataset bias, a common phenomenon in computer vision. To make semantic segmentation more useful in practice, one can exploit geometric constraints. Our main contribution is to show that these constraints can be cast conveniently as semi-supervised terms, which enforce the fact that the same class should be predicted for the projections of the same 3D location in different images. This is interesting as we can exploit general existing techniques developed for semi-supervised learning to efficiently incorporate the constraints. We show that this approach can efficiently and accurately learn to segment target sequences of ScanNet and our own target sequences using only annotations from SUNRGB-D, and geometric relations between the video frames of target sequences.