Physics Inspired Optimization on Semantic Transfer Features: An Alternative Method for Room Layout Estimation
This work addresses room layout estimation for indoor scene understanding, presenting an incremental improvement over existing methods.
The authors tackled room layout estimation in cluttered indoor scenes by proposing a method combining semantic transfer features and physics-inspired optimization, achieving higher accuracy than state-of-the-art methods on LSUN and Hedau datasets.
In this paper, we propose an alternative method to estimate room layouts of cluttered indoor scenes. This method enjoys the benefits of two novel techniques. The first one is semantic transfer (ST), which is: (1) a formulation to integrate the relationship between scene clutter and room layout into convolutional neural networks; (2) an architecture that can be end-to-end trained; (3) a practical strategy to initialize weights for very deep networks under unbalanced training data distribution. ST allows us to extract highly robust features under various circumstances, and in order to address the computation redundance hidden in these features we develop a principled and efficient inference scheme named physics inspired optimization (PIO). PIO's basic idea is to formulate some phenomena observed in ST features into mechanics concepts. Evaluations on public datasets LSUN and Hedau show that the proposed method is more accurate than state-of-the-art methods.