Research on Interior Design Method Based on Deep Learning

Author(s):  
Ming Lei
IEEE Access ◽  
2021 ◽  
pp. 1-1
Author(s):  
Aimin Zhou ◽  
Hongbin Liu ◽  
Shutao Zhang ◽  
Jinyan Ouyang

2020 ◽  
Vol 15 (2) ◽  
pp. 48-58
Author(s):  
I Kadek Dwi Noorwatha ◽  
Putu Ari Darmastuti ◽  
Ni Luh Kadek Resi Kerdiati

This research is a fundamental research that seeks to formulate an interior design method based on local culture and the industrial revolution 4.0 called 'Rachana Vidhi'. The research problem arises from the urgent need for the formulation of an ideal interior design method, which combines the development of local culture, the needs of the interior design industry and implements the spirit of the industrial revolution 4.0. The research method uses a qualitative document study approach specifically with the systematic review method, which is combined with the comparative method. The reseach results of the 'Rachana Vidhi' method have been discussed using the basic framework of the stages of the HDII professional organization as a synergy between academics and professional organizations. The method also balances knowledge and abilities between academics and practitioners with the 'research based design' paradigm. In the context of cultural development, the interior design method 'Rachana Vidhi' has been filled in at the ‘Predesain’ stage especially at step no. 15 Cultural Exploration, as part of the drafting of interior design concepts. Synergy with the industrial revolution 4.0 on the interior design method 'Rachana Vidhi' is applied to the stages of Input, Design, Conceptual Design and Design Development. Industrial revolution 4.0 application used is for insight searching, data collecting and modeling.


2020 ◽  
Vol 34 (10) ◽  
pp. 13975-13976 ◽  
Author(s):  
İlkay Yıldız ◽  
Esra Ataer-Cansızoğlu ◽  
Hantian Liu ◽  
Peter Golbus ◽  
Ozan Tezcan ◽  
...  

We present a deep learning based room image retrieval framework that is based on style understanding. Given a dataset of room images labeled by interior design experts, we map the noisy style labels to comparison labels. Our framework learns the style spectrum of each image from the generated comparisons and makes significantly more accurate recommendations compared to discrete classification baselines.


2019 ◽  
Vol 44 (3) ◽  
pp. 36-39
Author(s):  
Liang Zhang

To achieve the most intuitive display of interior design effect, the concept, characteristics, expression mode, application scope and basic types of virtual reality display design are expounded from the perspective of three dimension (3d) virtual reality technology, and the advantages and disadvantages of 3d modeling speed and panoramic visualization display are analyzed. The results show that through this research and practice, a series of 3d production techniques for interior design space, such as mapping technology, lighting technology, modeling technology, etc., are summarized. These technologies can effectively make use of ordinary computer to make and operate virtual reality and makes an exploratory attempt for the promotion of 3d technology in interior design industry in the future. In this study, it provides a design fulcrum for the development of indoor furniture display under the new economic conditions, which is of great practical significance for the healthy and sustainable development of interior design industry.


Jurnal Patra ◽  
2020 ◽  
Vol 2 (1) ◽  
pp. 27-36
Author(s):  
Hilmi Dzakaaul Islam ◽  
I Wayan Yogik Adnyana Putra ◽  
Ni Wayan Ardiarani Utami

ABSTRACT Traditional markets with their special characteristics and cultural values are still cinsidered dirty and unorganized places. This view is also found in Ngentak Traditional Market, Dayu Village, Kab. Blitar. This 50 years old market has many problems include patchy roofs that make the heat of the sun go inside and when it rains, making the market floor muddy, and it makes market feel so dirty. The absence of a zoning system makes buyers confused when shopping, the narrow circulation of space reduces the convenience of activities in the market. The market office on the 2nd (second) floor also has a problem with unstandard staircase, making user feel uncomfortable. The purpose of this redesign is to redesign traditional markets according to the interior design and market building standards, but also applying designs that still retain the characteristics, cultural value of traditional markets and the surrounding environment. The redesign used glass box design method with structured and systematic parameters based on facts. The results is redesign of the Ngentak Market with contemporary themes and local ethnic concepts typical of Blitar Regency that give new designs and arrangements to traditional markets, so that can overcome the problems that exist today to change the outlook on traditional markets to be positive. Key words : Traditional Market, Zoning, Contemporary, Local Ethnic.   ABSTRAK Pasar tradisional dengan ciri khas dan nilai kultural yang ada di dalamnya masih dipandang sebagai tempat yang kotor, kumuh dan tidak tertata. Pandangan tersebut juga dijumpai di Pasar Tradisional Ngentak, Desa Dayu, Kabupaten Blitar. Permasalahan pasar yang sudah berumur lebih dari 50 tahun ini diantaranya terlihat atap tambal sulam dengan bahan seadanya membuat panas terik matahari masuk ke dalam dan saat hujan air bocor menjadikan lantai pasar becek, serta menambah nuansa pasar menjadi kotor dan kumuh. Tidak adanya sistem zonasi pedagang membuat bingung pembeli saat berbelanja, sirkulasi ruang gerak yang sempit mengurangi kenyamanan beraktivitas di dalam pasar. Kantor pasar yang berada di lantai 2 (dua) juga mempunyai permasalahan ruang yaitu akses tangga sempit yang tidak sesuai standar membuat pengguna ruang merasa tidak nyaman. Tujuan perancangan ini adalah meredesain pasar tradisional sesuai standar ilmu desain interior dan standar bangunan pasar, selain itu juga dengan mengaplikasikan desain yang tetap mempertahankan ciri khas, nilai kultural pasar tradisional dan lingkungan sekitar. Metode perancangan yang digunakan yaitu metode desain glass box dengan parameter terstruktur dan sistematis berdasarkan fakta yang ada. Hasil yang diperoleh adalah perancangan redesain Pasar Ngentak dengan tema kontemporer dan konsep etnik lokal khas Kabupaten Blitar yang memberi desain dan tatanan baru pada pasar tradisional, sehingga bisa mengatasi permasalahan ruang yang ada sekaligus mengubah pandangan tentang pasar tradisional menjadi positif. Kata Kunci : Pasar Tradisional, Zonasi, Kontemporer, Etnik lokal.


2021 ◽  
Author(s):  
Xuecong Sun ◽  
Han Jia ◽  
Yuzhen Yang ◽  
Han Zhao ◽  
Yafeng Bi ◽  
...  

Abstract From ancient to modern times, acoustic structures have been used to control the propagation of acoustic waves. However, the design of acoustic structures has remained a time-consuming and computational resource-consuming iterative process. In recent years, deep learning has attracted unprecedented attention for its ability to tackle hard problems with large datasets, achieving state-of-the-art results in various tasks. In this work, an acoustic structure design method is proposed based on deep learning. Taking the design of multiorder Helmholtz resonator as an example, we experimentally demonstrate the effectiveness of the proposed method. Our method is not only able to give a very accurate prediction of the geometry of acoustic structures with multiple strong-coupling parameters, but also capable of improving the performance of evolutionary approaches in optimization for a desired property. Compared with the conventional numerical methods, our method is more efficient, universal and automatic, and it has a wide range of potential applications, such as speech enhancement, sound absorption and insulation.


2020 ◽  
Vol 10 (15) ◽  
pp. 5284 ◽  
Author(s):  
Houdi Xiao ◽  
Zhipeng Qu ◽  
Mingyun Lv ◽  
Yi Jiang ◽  
Chuanzhi Wang ◽  
...  

Traditional digital camouflage is mainly designed for a single background and state. Its camouflage performance is appealing in the specified time and place, but with the change of place, season, and time, its camouflage performance is greatly weakened. Therefore, camouflage technology, which can change with the environment in real-time, is the inevitable development direction of the military camouflage field in the future. In this paper, a fast-self-adaptive digital camouflage design method based on deep learning is proposed for the new generation of adaptive optical camouflage. Firstly, we trained a YOLOv3 model that could identify four typical military targets with mean average precision (mAP) of 91.55%. Secondly, a pre-trained deepfillv1 model was used to design the preliminary camouflage texture. Finally, the preliminary camouflage texture was standardized by the k-means algorithm. The experimental results show that the camouflage pattern designed by our proposed method is consistent with the background in texture and semantics, and has excellent camouflage performance in optical camouflage. Meanwhile, the whole pattern generation process takes a short time, less than 0.4 s, which meets the camouflage design requirements of the near-real-time camouflage in the future.


Author(s):  
Minsup Kim ◽  
Kichul Park ◽  
Wonsang Kim ◽  
Sangwon Jung ◽  
Art E. Cho

Molecules ◽  
2020 ◽  
Vol 25 (24) ◽  
pp. 5786
Author(s):  
Takafumi Aizawa

It was verified that deep learning can be used in creating multilayer membranes with multiple porosities using the CO2-assisted polymer compression (CAPC) method. To perform training while reducing the number of experimental data as much as possible, the experimental data of the compression behavior of two layers were expanded to three layers for training, but sufficient accuracy could not be obtained. However, the accuracy was dramatically improved by adding the experimental data of the three layers. The possibility of only simulating process results without the necessity for a model is a merit unique to deep learning. Overall, in this study, the results show that by devising learning data, deep learning is extremely effective in designing multilayer membranes using the CAPC method.


Sign in / Sign up

Export Citation Format

Share Document