Learning HDR illumination from LDR panorama images

Abstract For indoor scenes, the fourth-order spherical harmonic function is used to model the illumination, resulting in that 48 spherical harmonic coefficients are used to represent the whole scene. The illumination contained in the low dynamic range image is insufficient, so high dynamic range environment maps are adopted in this part, and the aim is to predict spherical harmonic coefficients of the corresponding high dynamic range image from the low dynamic range image. For this problem, the MSE loss function is used in this paper. Experiments verify the effectiveness of our method. The final visual results show that our method can predict accurate spherical harmonic coefficients, and the recovered luminance is realistic.

[1]  Jean-François Lalonde,et al.  Lighting Estimation in Outdoor Image Collections , 2014, 2014 2nd International Conference on 3D Vision.

[2]  Alexander Wilkie,et al.  An analytic model for full spectral sky-dome radiance , 2012, ACM Trans. Graph..

[3]  Sanja Fidler,et al.  Find your way by observing the sun and other semantic cues , 2016, 2017 IEEE International Conference on Robotics and Automation (ICRA).

[4]  Wolfgang Heidrich,et al.  Ldr2Hdr: on-the-fly reverse tone mapping of legacy video and photographs , 2007, SIGGRAPH 2007.

[5]  Ko Nishino,et al.  Reflectance and Illumination Recovery in the Wild , 2016, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[6]  Derek Nowrouzezahrai,et al.  Learning hatching for pen-and-ink illustration of surfaces , 2012, TOGS.

[7]  Giuseppe Claudio Guarnera,et al.  Woven Fabric Model Creation from a Single Image , 2017, ACM Trans. Graph..

[8]  Jinsong Zhang,et al.  Learning High Dynamic Range from Outdoor Panoramas , 2017, 2017 IEEE International Conference on Computer Vision (ICCV).

[9]  Yannick Hold-Geoffroy,et al.  Deep Outdoor Illumination Estimation , 2016, 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[10]  Huimin Lu,et al.  Ternary Adversarial Networks With Self-Supervision for Zero-Shot Cross-Modal Retrieval , 2020, IEEE Transactions on Cybernetics.

[11]  Zhenbing Liu,et al.  MADNet: A Fast and Lightweight Network for Single-Image Super Resolution , 2020, IEEE Transactions on Cybernetics.

[12]  Huimin Lu,et al.  Motor Anomaly Detection for Aerial Unmanned Vehicles Using Temperature Sensor , 2018 .

[13]  Thomas Brox,et al.  Striving for Simplicity: The All Convolutional Net , 2014, ICLR.

[14]  Huimin Lu,et al.  Brain Intelligence: Go beyond Artificial Intelligence , 2017, Mobile Networks and Applications.

[15]  Jitendra Malik,et al.  Shape, Illumination, and Reflectance from Shading , 2015, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[16]  Stephen Lin,et al.  Faces as Lighting Probes via Unsupervised Deep Highlight Extraction , 2018, ECCV.

[17]  Xin Jin,et al.  Painting completion with generative translation models , 2018, Multimedia Tools and Applications.

[18]  Alexander Wilkie,et al.  Adding a Solar-Radiance Function to the Hošek-Wilkie Skylight Model , 2013, IEEE Computer Graphics and Applications.

[19]  Qunsheng Peng,et al.  Online illumination estimation of outdoor scenes based on videos containing no shadow area , 2013, Science China Information Sciences.

[20]  Jean-François Lalonde,et al.  Learning to Estimate Indoor Lighting from 3D Objects , 2018, 2018 International Conference on 3D Vision (3DV).

[21]  Xiaochun Cheng,et al.  Introduction of Key Problems in Long-Distance Learning and Training , 2018, Mob. Networks Appl..

[22]  Hanwu Chen,et al.  Construction of punctured and extended quantum codes over GF(2) , 2012, Science China Information Sciences.

[23]  Xiaokun Zhang,et al.  Sun orientation estimation from a single image using short-cuts in DCNN , 2019, Optics & Laser Technology.

[24]  Ersin Yumer,et al.  Learning to predict indoor illumination from a single image , 2017, ACM Trans. Graph..

[25]  Ruijun Liu,et al.  Effect of economically friendly acustimulation approach against cybersickness in video-watching tasks using consumer virtual reality devices. , 2019, Applied ergonomics.