Towards Full-to-Empty Room Generation with Structure-Aware Feature Encoding and Soft Semantic Region-Adaptive Normalization

TL;DR

This paper introduces softSEAN, a differentiable normalization module for transforming furnished room images into background-only images, improving realism and structural consistency in scene editing tasks.

Contribution

The paper proposes a novel fully differentiable soft semantic region-adaptive normalization (softSEAN) module for scene layout generation, enhancing existing models in room background removal.

Findings

Outperforms existing methods quantitatively and qualitatively

Mitigates training complexity and non-differentiability issues

Applicable as a drop-in module for various models

Abstract

The task of transforming a furnished room image into a background-only is extremely challenging since it requires making large changes regarding the scene context while still preserving the overall layout and style. In order to acquire photo-realistic and structural consistent background, existing deep learning methods either employ image inpainting approaches or incorporate the learning of the scene layout as an individual task and leverage it later in a not fully differentiable semantic region-adaptive normalization module. To tackle these drawbacks, we treat scene layout generation as a feature linear transformation problem and propose a simple yet effective adjusted fully differentiable soft semantic region-adaptive normalization module (softSEAN) block. We showcase the applicability in diminished reality and depth estimation tasks, where our approach besides the advantages of mitigating training complexity and non-differentiability issues, surpasses the compared methods both quantitatively and qualitatively. Our softSEAN block can be used as a drop-in module for existing discriminative and generative models. Implementation is available on vcl3d.github.io/PanoDR/.