iBARLE: imBalance-Aware Room Layout Estimation

TL;DR

iBARLE introduces a comprehensive framework for room layout estimation that addresses dataset imbalance issues through appearance variation, structural mix-up, and occlusion-aware objectives, achieving state-of-the-art results.

Contribution

The paper proposes the iBARLE framework with novel modules for appearance variation, structural mix-up, and occlusion-aware training, improving model robustness and accuracy.

Findings

iBARLE outperforms existing methods on ZInD dataset

Modules improve generalization to diverse room structures

Effective handling of occlusions in complex layouts

Abstract

Room layout estimation predicts layouts from a single panorama. It requires datasets with large-scale and diverse room shapes to train the models. However, there are significant imbalances in real-world datasets including the dimensions of layout complexity, camera locations, and variation in scene appearance. These issues considerably influence the model training performance. In this work, we propose the imBalance-Aware Room Layout Estimation (iBARLE) framework to address these issues. iBARLE consists of (1) Appearance Variation Generation (AVG) module, which promotes visual appearance domain generalization, (2) Complex Structure Mix-up (CSMix) module, which enhances generalizability w.r.t. room structure, and (3) a gradient-based layout objective function, which allows more effective accounting for occlusions in complex layouts. All modules are jointly trained and help each other to achieve the best performance. Experiments and ablation studies based on ZInD~\cite{cruz2021zillow} dataset illustrate that iBARLE has state-of-the-art performance compared with other layout estimation baselines.