{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,11,19]],"date-time":"2024-11-19T19:13:46Z","timestamp":1732043626665,"version":"3.28.0"},"reference-count":98,"publisher":"IEEE","license":[{"start":{"date-parts":[[2024,6,16]],"date-time":"2024-06-16T00:00:00Z","timestamp":1718496000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,6,16]],"date-time":"2024-06-16T00:00:00Z","timestamp":1718496000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/100000001","name":"NSF","doi-asserted-by":"publisher","award":["2105819"],"id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2024,6,16]]},"DOI":"10.1109\/cvpr52733.2024.02278","type":"proceedings-article","created":{"date-parts":[[2024,9,16]],"date-time":"2024-09-16T17:34:53Z","timestamp":1726508093000},"page":"24130-24141","source":"Crossref","is-referenced-by-count":2,"title":["Alchemist: Parametric Control of Material Properties with Diffusion Models"],"prefix":"10.1109","author":[{"given":"Prafull","family":"Sharma","sequence":"first","affiliation":[{"name":"MIT CSAIL"}]},{"given":"Varun","family":"Jampani","sequence":"additional","affiliation":[{"name":"Google Research"}]},{"given":"Yuanzhen","family":"Li","sequence":"additional","affiliation":[{"name":"Google Research"}]},{"given":"Xuhui","family":"Jia","sequence":"additional","affiliation":[{"name":"Google Research"}]},{"given":"Dmitry","family":"Lagun","sequence":"additional","affiliation":[{"name":"Google Research"}]},{"given":"Fredo","family":"Durand","sequence":"additional","affiliation":[{"name":"Google Research"}]},{"given":"Bill","family":"Freeman","sequence":"additional","affiliation":[{"name":"MIT CSAIL"}]},{"given":"Mark","family":"Matthews","sequence":"additional","affiliation":[{"name":"Google Research"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01767"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1145\/2809796"},{"key":"ref3","first-page":"18392","article-title":"In-structpix2pix: Learning to follow image editing instructions","volume-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","author":"Brooks"},{"key":"ref4","article-title":"Physically based shading at disney","author":"Burley","year":"2012","journal-title":"ACM SIGGRAPH 2012 Courses"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.02062"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00229"},{"key":"ref7","article-title":"Subject-driven text-to-image generation via apprenticeship learning","author":"Chen","year":"2023","journal-title":"arXiv preprint"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i2.27886"},{"volume-title":"Blender - a 3D modelling and rendering package","year":"2018","author":"Online Community","key":"ref9"},{"key":"ref10","article-title":"Attribute-centric compositional text-to-image generation","author":"Cong","year":"2023","journal-title":"arXiv preprint"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1145\/357290.357293"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19836-6_6"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1111\/cgf.14446"},{"key":"ref14","first-page":"8780","article-title":"Diffusion models beat gans on image synthesis","volume":"34","author":"Dhariwal","year":"2021","journal-title":"Advances in neural information processing systems"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1145\/2661229.2661282"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1167\/10.4.8"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1016\/j.visres.2013.11.004"},{"issue":"5","key":"ref18","first-page":"3","article-title":"Real-world illumination and the perception of surface re-flectance properties","volume-title":"Journal of vision","volume":"3","author":"Fleming","year":"2003"},{"key":"ref19","article-title":"Scenescape: Text-driven consistent scene generation","volume":"abs\/2302.01133","author":"Fridman","year":"2023","journal-title":"ArXiv"},{"key":"ref20","article-title":"An image is worth one word: Personalizing text-to-image generation using textual inversion","author":"Gal","year":"2022","journal-title":"arXiv preprint"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00694"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1145\/3422622"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01808"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01808"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1145\/142920.134073"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1145\/127719.122738"},{"key":"ref27","article-title":"Prompt-to-prompt image editing with cross attention control","author":"Hertz","year":"2022","journal-title":"arXiv preprint"},{"key":"ref28","first-page":"6840","article-title":"Denoising diffusion probabilistic models","volume":"33","author":"Ho","year":"2020","journal-title":"Advances in neural information processing systems"},{"issue":"1","key":"ref29","first-page":"2249","article-title":"Cascaded diffusion models for high fidelity image generation","volume":"23","author":"Ho","year":"2022","journal-title":"The Journal of Machine Learning Research"},{"key":"ref30","article-title":"Classifier-free diffusion guidance","author":"Ho","year":"2022","journal-title":"arXiv preprint"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00727"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.59"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00976"},{"key":"ref34","first-page":"26565","article-title":"Elucidating the design space of diffusion-based generative models","volume":"35","author":"Karras","year":"2022","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52729.2023.00582"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1145\/1141911.1141937"},{"key":"ref37","first-page":"2426","article-title":"Dif-fusionclip: Text-guided diffusion models for robust image manipulation","volume-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","author":"Kim"},{"key":"ref38","article-title":"Adam: A method for stochastic optimization","author":"Kingma","year":"2014","journal-title":"arXiv preprint"},{"key":"ref39","article-title":"Auto-encoding variational bayes","author":"Kingma","year":"2013","journal-title":"arXiv preprint"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00371"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00192"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.248"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00853"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58621-8_6"},{"key":"ref45","article-title":"Syncdreamer: Learning to generate multiview-consistent images from a single-view image","author":"Liu","year":"2023","journal-title":"arXiv preprint"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-33783-3_42"},{"key":"ref47","article-title":"Dpm-solver++: Fast solver for guided sampling of diffusion probabilistic models","author":"Lu","year":"2022","journal-title":"arXiv preprint"},{"key":"ref48","article-title":"Subject-diffusion: Open domain personalized text-to-image generation without test-time fine-tuning","author":"Ma","year":"2023","journal-title":"arXiv preprint"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.2352\/J.ImagingSci.Technol.2021.65.6.060406"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1016\/j.cub.2012.08.009"},{"key":"ref51","article-title":"Sdedit: Guided image synthesis and editing with stochastic differential equations","author":"Meng","year":"2021","journal-title":"arXiv preprint"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58452-8_24"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00585"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1016\/j.visres.2011.11.010"},{"key":"ref55","article-title":"T2i-adapter: Learning adapters to dig out more controllable ability for text-to-image diffusion models","author":"Mou","year":"2023","journal-title":"arXiv preprint"},{"key":"ref56","article-title":"Glide: Towards photorealistic image generation and editing with text-guided diffusion models","author":"Nichol","year":"2021","journal-title":"arXiv preprint"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1364\/JOSAA.15.002951"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1167\/4.9.4"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1167\/10.9.5"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00294"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00209"},{"key":"ref62","article-title":"Dreamfusion: Text-to-3d using 2d diffusion","author":"Poole","year":"2022","journal-title":"arXiv preprint"},{"key":"ref63","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"International conference on machine learning","author":"Radford"},{"key":"ref64","article-title":"Dream-booth3d: Subject-driven text-to-3d generation","author":"Raj","year":"2023","journal-title":"arXiv preprint"},{"issue":"2","key":"ref65","article-title":"Hierarchical text-conditional image generation with clip latents","volume":"1","author":"Ramesh","year":"2022","journal-title":"arXiv preprint"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00161"},{"key":"ref67","first-page":"10674","article-title":"High-resolution image synthesis with latent diffusion models. 2022 ieee","volume-title":"CVF Conference on Computer Vision and Pattern Recognition (CVPR)","author":"Rombach"},{"key":"ref68","article-title":"Dreambooth: Fine tuning text-to-image diffusion models for subject-driven generation","author":"Ruiz","year":"2022","journal-title":"arXiv preprint"},{"key":"ref69","article-title":"Hyperdreambooth: Hypernetworks for fast personalization of text-to-image models","author":"Ruiz","year":"2023","journal-title":"arXiv preprint"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1145\/3528233.3530757"},{"key":"ref71","first-page":"36479","article-title":"Photorealistic text-to-image diffusion models with deep language understanding.","volume":"35","author":"Saharia","year":"2022","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00046"},{"key":"ref73","article-title":"Let 2d diffusion model know 3d-consistency for robust text-to-3d generation","author":"Seo","year":"2023","journal-title":"arXiv preprint"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.1145\/3592390"},{"key":"ref75","article-title":"Instant-booth: Personalized text-to-image generation without test-time finetuning","author":"Shi","year":"2023","journal-title":"arXiv preprint"},{"volume-title":"Mvdream: Multi-view diffusion for 3d generation","year":"2023","author":"Shi","key":"ref76"},{"key":"ref77","first-page":"2256","article-title":"Deep unsupervised learning using nonequilibrium thermodynamics","volume-title":"International conference on machine learning","author":"Sohl-Dickstein"},{"key":"ref78","article-title":"Styledrop: Text-to-image generation in any style","author":"Sohn","year":"2023","journal-title":"arXiv preprint"},{"key":"ref79","article-title":"Generative modeling by estimating gradients of the data distribution","volume":"32","author":"Song","year":"2019","journal-title":"Advances in neural information processing systems"},{"key":"ref80","doi-asserted-by":"publisher","DOI":"10.1038\/s41562-021-01097-6"},{"key":"ref81","doi-asserted-by":"publisher","DOI":"10.1111\/cgf.14765"},{"key":"ref82","article-title":"De-net: Dynamic text-guided image editing adversarial networks","author":"Tao","year":"2022","journal-title":"arXiv preprint"},{"key":"ref83","article-title":"Textmesh: Generation of realistic 3d meshes from text prompts","volume":"abs\/2304.12439","author":"Tsalicoglou","year":"2023","journal-title":"ArXiv"},{"key":"ref84","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00191"},{"key":"ref85","doi-asserted-by":"publisher","DOI":"10.1145\/3588432.3591560"},{"key":"ref86","article-title":"p+: Extended textual conditioning in text-to-image generation","author":"Voynov","year":"2023","journal-title":"arXiv preprint"},{"volume-title":"Score jacobian chaining: Lifting pretrained 2d diffusion models for 3d generation","year":"2022","author":"Wang","key":"ref87"},{"key":"ref88","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2003.819861"},{"key":"ref89","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01461"},{"key":"ref90","article-title":"Fastcomposer: Tuning-free multi-subject image generation with localized attention","volume-title":"arXiv preprint","author":"Xiao","year":"2023"},{"key":"ref91","article-title":"Instructp2p: Learning to edit 3d point clouds with text instructions","author":"Xu","year":"2023","journal-title":"arXiv e-prints"},{"key":"ref92","article-title":"Ip-adapter: Text compatible image prompt adapter for text-to-image diffusion models","author":"Ye","year":"2023","journal-title":"arXiv preprint"},{"key":"ref93","article-title":"Edit-diffnerf: Editing 3d neural radiance fields using 2d diffusion model","author":"Yu","year":"2023","journal-title":"arXiv e-prints"},{"key":"ref94","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00355"},{"key":"ref95","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00068"},{"key":"ref96","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2023\/201"},{"key":"ref97","doi-asserted-by":"publisher","DOI":"10.1145\/3610548.3618190"},{"key":"ref98","doi-asserted-by":"publisher","DOI":"10.1111\/cgf.14057"}],"event":{"name":"2024 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","start":{"date-parts":[[2024,6,16]]},"location":"Seattle, WA, USA","end":{"date-parts":[[2024,6,22]]}},"container-title":["2024 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/10654794\/10654797\/10656698.pdf?arnumber=10656698","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,9,19]],"date-time":"2024-09-19T06:26:03Z","timestamp":1726727163000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10656698\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,6,16]]},"references-count":98,"URL":"https:\/\/doi.org\/10.1109\/cvpr52733.2024.02278","relation":{},"subject":[],"published":{"date-parts":[[2024,6,16]]}}}