{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T17:40:12Z","timestamp":1777657212048,"version":"3.51.4"},"reference-count":46,"publisher":"IEEE","license":[{"start":{"date-parts":[[2019,9,1]],"date-time":"2019-09-01T00:00:00Z","timestamp":1567296000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2019,9,1]],"date-time":"2019-09-01T00:00:00Z","timestamp":1567296000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2019,9,1]],"date-time":"2019-09-01T00:00:00Z","timestamp":1567296000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2019,9]]},"DOI":"10.1109\/icip.2019.8803821","type":"proceedings-article","created":{"date-parts":[[2019,8,26]],"date-time":"2019-08-26T19:32:48Z","timestamp":1566847968000},"page":"66-70","source":"Crossref","is-referenced-by-count":97,"title":["Photorealistic Image Synthesis for Object Instance Detection"],"prefix":"10.1109","author":[{"given":"Tomas","family":"Hodan","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Vibhav","family":"Vineet","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ran","family":"Gal","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Emanuel","family":"Shalev","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jon","family":"Hanzelka","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Treb","family":"Connell","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Pedro","family":"Urbina","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Sudipta N.","family":"Sinha","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Brian","family":"Guenter","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref39","year":"0","journal-title":"Evermotion"},{"key":"ref38","year":"0","journal-title":"Color sensor"},{"key":"ref33","article-title":"Learning an appearance-based gaze estimator from one million synthesised images","year":"2016","journal-title":"Proceedings of the Ninth Biennial ACM Symposium on Eye Tracking Research & Applications"},{"key":"ref32","article-title":"Rendering of eyes for eye-shape registration and gaze estimation","year":"2015","journal-title":"ICCV"},{"key":"ref31","article-title":"Implicit 3D orientation learning for 6D object detection from RGB images","year":"2018","journal-title":"ECCV"},{"key":"ref30","article-title":"Training deep networks with synthetic data: Bridging the reality gap by domain randomization","year":"2018","journal-title":"arXiv preprint arXiv 1804 07612"},{"key":"ref37","year":"0","journal-title":"MURA"},{"key":"ref36","article-title":"A summary of team MIT’s approach to the Amazon Picking Challenge 2015","year":"2016","journal-title":"ArXiv preprint arXiv 1604 03639"},{"key":"ref35","article-title":"BOP: Benchmark for 6D object pose estimation","year":"2018","journal-title":"ECCV"},{"key":"ref34","article-title":"Learning from simulated and unsupervised images through adversarial training","year":"2017","journal-title":"CVPR"},{"key":"ref10","article-title":"Physically-based rendering for indoor scene understanding using convolutional neural networks","year":"2017","journal-title":"CVPR"},{"key":"ref40","article-title":"FLARE: fast layout for augmented reality applications","year":"2014","journal-title":"ISMA 2014"},{"key":"ref11","article-title":"Arnold: A brute-force production path tracer","year":"2018","journal-title":"TOG"},{"key":"ref12","year":"2016","journal-title":"Physically Based Rendering From Theory to Implementation"},{"key":"ref13","year":"2009","journal-title":"OpenGL Programming Guide The Official Guide to Learning OpenGL Version 1 2"},{"key":"ref14","year":"2015","journal-title":"Fundamentals of Computer Graphics"},{"key":"ref15","article-title":"Cut, paste and learn: Surprisingly easy synthesis for instance detection","year":"2017","journal-title":"ICCV"},{"key":"ref16","article-title":"On pre-trained image features and synthetic images for deep learning","year":"2018","journal-title":"ECCVW"},{"key":"ref17","article-title":"SSD-6D: Making RGB-based 3D detection and 6D pose estimation great again","year":"2017","journal-title":"ICCV"},{"key":"ref18","article-title":"BB8: a scalable, accurate, robust to partial occlusion method for predicting the 3D poses of challenging objects without using depth","year":"2017","journal-title":"ICCV"},{"key":"ref19","article-title":"Flownet: Learning optical flow with convolutional networks","year":"2015","journal-title":"ICCV"},{"key":"ref28","article-title":"SceneNet RGB-D: Can 5M synthetic images beat generic imagenet pre-training on indoor segmentation?","year":"2017","journal-title":"ICCV"},{"key":"ref4","article-title":"Model based training, detection and pose estimation of texture-less 3D objects in heavily cluttered scenes","year":"2012","journal-title":"ACCV"},{"key":"ref27","article-title":"Understanding real world indoor scenes with synthetic data","year":"2016","journal-title":"CVPR"},{"key":"ref3","article-title":"Learning 6D object pose estimation using 3D object coordinates","year":"2014","journal-title":"ECCV"},{"key":"ref6","article-title":"Render for CNN: viewpoint estimation in images using CNNs trained with rendered 3D model views","year":"2015","journal-title":"ICCV"},{"key":"ref29","article-title":"Domain randomization for transferring deep neural networks from simulation to the real world","year":"2017","journal-title":"IROS"},{"key":"ref5","article-title":"Playing for data: Ground truth from computer games","year":"2016","journal-title":"ECCV"},{"key":"ref8","article-title":"A comprehensive survey on domain adaptation for visual applications","year":"2017","journal-title":"Domain adaptations for computer vision applications"},{"key":"ref7","article-title":"Beyond sharing weights for deep domain adaptation","year":"2018","journal-title":"TPAMI"},{"key":"ref2","article-title":"A dataset for improved RGBD-based object detection and pose estimation for warehouse pick-and-place","year":"2016","journal-title":"Proceedings of Robotics and Automation Letters"},{"key":"ref9","article-title":"CGIntrinsics: Better intrinsic image decomposition through physically-based rendering","year":"2018","journal-title":"ECCV"},{"key":"ref1","article-title":"Faster R-CNN: towards real-time object detection with region proposal networks","year":"2017","journal-title":"TPAMI"},{"key":"ref46","article-title":"An empirical study of context in object detection","year":"2009","journal-title":"CVPR"},{"key":"ref20","article-title":"Real-time seamless single shot 6d object pose prediction","year":"2018","journal-title":"CVPR"},{"key":"ref45","article-title":"Speed\/accuracy trade-offs for modern convolutional object detectors","year":"2017","journal-title":"CVPR"},{"key":"ref22","article-title":"How useful is photo-realistic rendering for visual learning?","year":"2016","journal-title":"ECCV"},{"key":"ref21","article-title":"Modeling visual context is key to augmenting object detection datasets","year":"2018","journal-title":"ECCV"},{"key":"ref42","article-title":"Deep residual learning for image recognition","year":"2016","journal-title":"CVPR"},{"key":"ref24","article-title":"Playing for benchmarks","year":"2017","journal-title":"ICCV"},{"key":"ref41","article-title":"Indoor segmentation and support inference from rgbd images","year":"2012","journal-title":"ECCV"},{"key":"ref23","article-title":"Deep object pose estimation for semantic robotic grasping of household objects","year":"2018","journal-title":"CoRL"},{"key":"ref44","article-title":"Microsoft COCO: Common objects in context","year":"2014","journal-title":"ECCV"},{"key":"ref26","article-title":"Virtual worlds as proxy for multi-object tracking analysis","year":"2016","journal-title":"CVPR"},{"key":"ref43","article-title":"Inception-v4, inception-resnet and the impact of residual connections on learning","year":"2017","journal-title":"AAAI"},{"key":"ref25","article-title":"The SYNTHIA dataset: A large collection of synthetic images for semantic segmentation of urban scenes","year":"2016","journal-title":"CVPR"}],"event":{"name":"2019 IEEE International Conference on Image Processing (ICIP)","location":"Taipei, Taiwan","start":{"date-parts":[[2019,9,22]]},"end":{"date-parts":[[2019,9,25]]}},"container-title":["2019 IEEE International Conference on Image Processing (ICIP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/8791230\/8799366\/08803821.pdf?arnumber=8803821","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,7,18]],"date-time":"2022-07-18T14:49:55Z","timestamp":1658155795000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/8803821\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019,9]]},"references-count":46,"URL":"https:\/\/doi.org\/10.1109\/icip.2019.8803821","relation":{},"subject":[],"published":{"date-parts":[[2019,9]]}}}