在室內設計中，使空間內的家具間具有和諧的風格被視為相當重要的目標。過去風格分析的相關研究中，大多採用定義好的幾何特徵描述子來擷取特徵，並評估物體的相似度或合適度。然而，風格屬於一種抽象的概念，難以利用傳統幾何特徵描述子進行描述。而深度神經網路被宣稱具有強大的學習能力，足以模仿人類視覺神經的感知。因此，在這個研究中，我們使用三元組卷積神經網路(Triplet Convolutional Neural Network，Triplet CNN)來分析不同種類之間的三維家具模型（如：桌子和檯燈）之風格合適度。其中，相較於分析同種類家具之間的相似度，當家具具有截然不同的結構或是幾何元素時，分析兩個或多個不同種類的家具之間的合適度是十分困難的。在本篇論文中，我們採用了自己蒐集的數據集來進行實驗，其中包含了420個具有紋理及顏色資訊的三維家具模型。在這個數據集中，我們利用亞馬遜的群眾外包平台(Amazon Mechanical Turk，Amazon Mturk)來募集群眾對於風格合適度的偏好，並用此偏好來學習成對家具的風格合適度，以及評估我們預測結果的正確性。而最後的實驗結果證明了我們所提出的基於深度學習之家具風格合適度分析方法相較於其他類似的研究有更好的表現，且這個方法也可以成功地應用於家具推薦系統中。

Harmonizing the style of all the furniture placed within a constrained space/scene has been regarded as one of the most important tasks in interior design. Most previous style analysis works measure the style similarity or compatibility of the objects based on predefined geometric features extracted from 3D models. However," style" is a high-level semantic concept, which is difficult to be described explicitly by hand-crafted geometric features. Deep neural network has been claimed to have more powerful ability to mimic the perception of human visual cortex. Therefore, in this work we utilize Triplet Convolutional Neural Network (Triplet CNN) to analyze style compatibility between 3D furniture models of different classes (e.g., a table and a lamp). It should be noted that analyzing the style compatibility between two or more furniture of different classes is quite difficult, as the given furniture may have distinctive structures or geometric elements. We conducted experiments based on a collected dataset containing 420 textured 3D furniture models. A group of raters were recruited from Amazon Mechanical Turk (AMT) to evaluate the comparative suitability of paired models within the dataset. The experimental results reveal that the proposed furniture style compatibility method based on deep learning is better than the state-of-the-art method and can be used for furniture recommendation.

[1] V. Balntas, E. Johns, L. Tang, and K. Mikolajczyk. Pn-net: conjoined triple deep network for learning local image descriptors. arXiv preprint arXiv: 1601.05030, 2016.
[2] A. Bansal, B. Russell, and A. Gupta. Marr revisited: 2d-3d alignment via surface normal prediction. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pages 5965–5974, 2016.
[3] S. Bell and K. Bala. Learning visual similarity for product design with convolutional neural networks. ACM Transactions on Graphics (TOG), 34(4):98, 2015.
[4] A. X. Chang, T. Funkhouser, L. Guibas, P. Hanrahan, Q. Huang, Z. Li, S. Savarese, M. Savva, S. Song, H. Su, et al. Shapenet: An information-rich
3d model repository. arXiv preprint arXiv:1512.03012, 2015.
[5] K. Dev, K. Kim, N. Villar, and M. Lau. Improving style similarity metrics of 3d shapes. In Proceedings of the 42nd Graphics Interface Conference, pages 175–182. Canadian Information Processing Society, 2016.
[6] E. Garces, A. Agarwala, D. Gutierrez, and A. Hertzmann. A similarity measure for illustration style. ACM Transactions on Graphics (TOG), 33(4):93, 2014.
[7] E. Garces, A. Agarwala, A. Hertzmann, and D. Gutierrez. Style-based exploration of illustration datasets. Multimedia Tools and Applications, pages 1–20, 2016.
[8] H. Guo, J. Wang, Y. Gao, J. Li, and H. Lu. Multi-view 3d object retrieval with deep embedding network. IEEE Transactions on Image Processing, 25(12): 5526–5537, 2016.
[9] E. Hoffer and N. Ailon. Deep metric learning using triplet network. In International Workshop on Similarity-Based Pattern Recognition, pages 84–92. Springer, 2015.
[10] Q.-X. Huang, H. Su, and L. Guibas. Fine-grained semi-supervised labeling of large shape collections. ACM Transactions on Graphics (TOG), 32(6):190, 2013.
[11] Y. Jia, E. Shelhamer, J. Donahue, S. Karayev, J. Long, R. Girshick, S. Guadarrama, and T. Darrell. Caffe: Convolutional architecture for fast feature embedding. In Proceedings of the 22nd ACM International Conference on Multimedia, pages 675–678. ACM, 2014.
[12] A. Krizhevsky, I. Sutskever, and G. E. Hinton. Imagenet classification with deep convolutional neural networks. In Advances in Neural Information Processing Systems, pages 1097–1105, 2012.
[13] B. Kulis et al. Metric learning: A survey. Foundations and Trends® in Machine Learning, 5(4):287–364, 2013.
[14] I. Lim, A. Gehre, and L. Kobbelt. Identifying style of 3d shapes using deep metric learning. Computer Graphics Forum, 35(5):207–215, 2016.
[15] T. Liu, A. Hertzmann, W. Li, and T. Funkhouser. Style compatibility for 3d furniture models. ACM Transactions on Graphics (TOG), 34(4):85, 2015.
[16] G. L. López, A. P. P. Negrón, A. D. A. Jiménez, J. R. Rodríguez, and R. I. Paredes. Comparative analysis of shape descriptors for 3d objects. Multimedia Tools and Applications, pages 1–48.
[17] Z. Lun, E. Kalogerakis, and A. Sheffer. Elements of style: Learning perceptual shape style similarity. ACM Transactions on Graphics (TOG), 34(4):84, 2015.
[18] Y. Luo, T. Liu, D. Tao, and C. Xu. Decomposition-based transfer distance metric learning for image classification. IEEE Transactions on Image Processing, 23(9):3789–3801, 2014.
[19] M. Masoumi, C. Li, and A. B. Hamza. A spectral graph wavelet approach for nonrigid 3d shape retrieval. Pattern Recognition Letters, 83:339–348, 2016.
[20] P. O’Donovan, J. Lībeks, A. Agarwala, and A. Hertzmann. Exploratory font selection using crowdsourced attributes. ACM Transactions on Graphics
(TOG), 33(4):92, 2014.
[21] B. Saleh, M. Dontcheva, A. Hertzmann, and Z. Liu. Learning style similarity for searching infographics. In Proceedings of the 41st Graphics Interface Conference, pages 59–64. Canadian Information Processing Society, 2015.
[22] K. Simonyan and A. Zisserman. Very deep convolutional networks for largescale image recognition. arXiv preprint arXiv:1409.1556, 2014.
[23] J. M. Wang, D. J. Fleet, and A. Hertzmann. Multifactor gaussian process models for style-content separation. In Proceedings of the 24th International Conference on Machine Learning, pages 975–982. ACM, 2007.
[24] Y. Wang, Z. Xie, K. Xu, Y. Dou, and Y. Lei. An efficient and effective convolutional auto-encoder extreme learning machine network for 3d feature learning. Neurocomputing, 174:988–998, 2016.
[25] M. J. Wilber, I. S. Kwak, and S. J. Belongie. Cost-effective hits for relative similarity comparisons. In Second AAAI Conference on Human Computation and Crowdsourcing, 2014.
[26] P. Wohlhart and V. Lepetit. Learning descriptors for object recognition and 3d pose estimation. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pages 3109–3118, 2015.
[27] J. Xie, G. Dai, F. Zhu, E. Wong, and Y. Fang. Deepshape: Deep-learned shape descriptor for 3d shape retrieval. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2016.
[28] K. Xu, H. Li, H. Zhang, D. Cohen-Or, Y. Xiong, and Z.-Q. Cheng. Stylecontent separation by anisotropic part scales. ACM Transactions on Graphics (TOG), 29(6):184, 2010.
[29] M. E. Yumer, S. Chaudhuri, J. K. Hodgins, and L. B. Kara. Semantic shape editing using deformation handles. ACM Transactions on Graphics (TOG), 34(4):86, 2015.