Infusion: Internal Diffusion for Inpainting of Dynamic Textures and Complex Motion
Video inpainting is the task of filling a region in a video in a visually convincing manner It is very challenging due to the high dimensionality of the data and the temporal consistency required for obtaining convincing results. Recently, diffusion models have shown impressive results in modeling c...
Uložené v:
| Vydané v: | Computer graphics forum Ročník 44; číslo 2 |
|---|---|
| Hlavní autori: | , , , |
| Médium: | Journal Article |
| Jazyk: | English |
| Vydavateľské údaje: |
Oxford
Blackwell Publishing Ltd
01.05.2025
|
| Predmet: | |
| ISSN: | 0167-7055, 1467-8659 |
| On-line prístup: | Získať plný text |
| Tagy: |
Pridať tag
Žiadne tagy, Buďte prvý, kto otaguje tento záznam!
|
| Abstract | Video inpainting is the task of filling a region in a video in a visually convincing manner It is very challenging due to the high dimensionality of the data and the temporal consistency required for obtaining convincing results. Recently, diffusion models have shown impressive results in modeling complex data distributions, including images and videos. Such models remain nonetheless very expensive to train and to perform inference with, which strongly reduce their applicability to videos, and yields unreasonable computational loads. We show that in the case of video inpainting, thanks to the highly auto‐similar nature of videos, the training data of a diffusion model can be restricted to the input video and still produce very satisfying results. With this internal learning approach, where the training data is limited to a single video, our lightweight models perform very well with only half a million parameters, in contrast to the very large networks with billions of parameters typically found in the literature. We also introduce a new method for efficient training and inference of diffusion models in the context of internal learning, by splitting the diffusion process into different learning intervals corresponding to different noise levels of the diffusion process. We show qualitative and quantitative results, demonstrating that our method reaches or exceeds state of the art performance in the case of dynamic textures and complex dynamic backgrounds. |
|---|---|
| AbstractList | Video inpainting is the task of filling a region in a video in a visually convincing manner It is very challenging due to the high dimensionality of the data and the temporal consistency required for obtaining convincing results. Recently, diffusion models have shown impressive results in modeling complex data distributions, including images and videos. Such models remain nonetheless very expensive to train and to perform inference with, which strongly reduce their applicability to videos, and yields unreasonable computational loads. We show that in the case of video inpainting, thanks to the highly auto‐similar nature of videos, the training data of a diffusion model can be restricted to the input video and still produce very satisfying results. With this internal learning approach, where the training data is limited to a single video, our lightweight models perform very well with only half a million parameters, in contrast to the very large networks with billions of parameters typically found in the literature. We also introduce a new method for efficient training and inference of diffusion models in the context of internal learning, by splitting the diffusion process into different learning intervals corresponding to different noise levels of the diffusion process. We show qualitative and quantitative results, demonstrating that our method reaches or exceeds state of the art performance in the case of dynamic textures and complex dynamic backgrounds. |
| Author | Gousseau, Y. Almansa, A. Newson, A. Cherel, N. |
| Author_xml | – sequence: 1 givenname: N. surname: Cherel fullname: Cherel, N. organization: LTCI, Télécom Paris, Institut Polytechnique de Paris – sequence: 2 givenname: A. surname: Almansa fullname: Almansa, A. organization: MAP5, CNRS & Université Paris Cité – sequence: 3 givenname: Y. surname: Gousseau fullname: Gousseau, Y. organization: LTCI, Télécom Paris, Institut Polytechnique de Paris – sequence: 4 givenname: A. surname: Newson fullname: Newson, A. organization: ISIR, Sorbonne Université |
| BookMark | eNp1kN9LwzAQx4NMcJs--B8EfPKhW5K2SeubdG4OJoLM55Dlx-jokpq0uP33ZtZXD4477j7fg_tOwMg6qwG4x2iGY8zl3swYQgxdgTHOKEsKmpcjMEY49gzl-Q2YhHBACGWM5mPwsbamD7WzT3BtO-2taOCiNsMMGufjuBW17Wq7h87AxdmKYy3hVp-63usAhVWwcse20Sf45rqougXXRjRB3_3VKfhcvmyr12TzvlpXz5tEpqRASSbpboeNxIZqjXJR4kwQQklMxRRLkS6QlFqoMsWK5LpMy6IgSFGiFBUpSafgYbjbevfV69Dxg-svDwQet5iVmBZppB4HSnoXgteGt74-Cn_mGPGLZTxaxn8ti-x8YL_rRp__B3m1Wg6KH5LFbkU |
| Cites_doi | 10.1109/ICCV51070.2023.00961 10.1109/ICCV51070.2023.00684 10.1109/CVPR.2019.00594 10.1109/CVPR.2005.38 10.1109/CVPR52688.2022.01704 10.1109/CVPR.2019.00384 10.1109/CVPR.2018.00577 10.1109/CVPR52688.2022.00589 10.1109/CVPR.2018.00701 10.1109/CVPR52729.2023.02148 10.1007/978‐3‐030‐58610‐2_42 10.1109/ICCV.2009.5459159 10.1109/CVPR52729.2023.02161 10.1109/ICCV.2019.00281 10.1109/CVPR.2018.00068 10.1109/CVPR52733.2024.00684 10.1137/140954933 10.1109/CVPR52688.2022.00350 10.1145/3478513.3480546 10.1109/ICCV51070.2023.02106 10.1109/TPAMI.2022.3204461 10.1109/ICCV51070.2023.02121 10.1109/ICCV48922.2021.01431 10.1007/978‐3‐030‐01264‐9_20 10.1109/CVPR52688.2022.01117 10.1007/978‐3‐031‐19797‐0_5 10.1109/CVPR46437.2021.00374 10.1145/3528233.3530757 10.1109/ICCV.2019.00467 10.1145/2980179.2982398 10.1111/j.1467-8659.2012.03000.x 10.1109/CVPR52729.2023.02155 10.1145/3581783.3612200 10.1109/CVPR.2018.00652 10.1609/aaai.v37i8.26094 10.24963/ijcai.2023/199 10.1109/CVPR52729.2023.01770 10.1109/CVPR.2018.00984 10.1109/ICCV48922.2021.01378 10.1007/s41095-019-0145-0 10.1109/TPAMI.2007.60 |
| ContentType | Journal Article |
| Copyright | 2025 Eurographics ‐ The European Association for Computer Graphics and John Wiley & Sons Ltd. 2025 The Eurographics Association and John Wiley & Sons Ltd. |
| Copyright_xml | – notice: 2025 Eurographics ‐ The European Association for Computer Graphics and John Wiley & Sons Ltd. – notice: 2025 The Eurographics Association and John Wiley & Sons Ltd. |
| DBID | AAYXX CITATION 7SC 8FD JQ2 L7M L~C L~D |
| DOI | 10.1111/cgf.70070 |
| DatabaseName | CrossRef Computer and Information Systems Abstracts Technology Research Database ProQuest Computer Science Collection Advanced Technologies Database with Aerospace Computer and Information Systems Abstracts Academic Computer and Information Systems Abstracts Professional |
| DatabaseTitle | CrossRef Computer and Information Systems Abstracts Technology Research Database Computer and Information Systems Abstracts – Academic Advanced Technologies Database with Aerospace ProQuest Computer Science Collection Computer and Information Systems Abstracts Professional |
| DatabaseTitleList | CrossRef Computer and Information Systems Abstracts |
| DeliveryMethod | fulltext_linktorsrc |
| Discipline | Engineering |
| EISSN | 1467-8659 |
| EndPage | n/a |
| ExternalDocumentID | 10_1111_cgf_70070 CGF70070 |
| Genre | article |
| GrantInformation_xml | – fundername: MISTIC funderid: ANR‐19‐CE40‐005 – fundername: Futur et Ruptures – fundername: Institut Mines Télécom, Fondation Mines‐Télécom, and l'Institut Carnot TSN – fundername: French Research Agency – fundername: PostProdLEAP funderid: ANR‐19‐CE23‐0027‐01 – fundername: IDeGeN funderid: ANR‐21‐CE23‐0024 |
| GroupedDBID | .3N .4S .DC .GA .Y3 05W 0R~ 10A 15B 1OB 1OC 29F 31~ 33P 3SF 4.4 50Y 50Z 51W 51X 52M 52N 52O 52P 52S 52T 52U 52W 52X 5GY 5HH 5LA 5VS 66C 6J9 702 7PT 8-0 8-1 8-3 8-4 8-5 8UM 8VB 930 A03 AAESR AAEVG AAHQN AAMMB AAMNL AANHP AANLZ AAONW AASGY AAXRX AAYCA AAZKR ABCQN ABCUV ABDBF ABDPE ABEML ABPVW ACAHQ ACBWZ ACCZN ACFBH ACGFS ACPOU ACRPL ACSCC ACUHS ACXBN ACXQS ACYXJ ADBBV ADEOM ADIZJ ADKYN ADMGS ADMLS ADNMO ADOZA ADXAS ADZMN AEFGJ AEGXH AEIGN AEIMD AEMOZ AENEX AEUYR AEYWJ AFBPY AFEBI AFFNX AFFPM AFGKR AFWVQ AFZJQ AGHNM AGQPQ AGXDD AGYGG AHBTC AHEFC AHQJS AIDQK AIDYY AITYG AIURR AJXKR AKVCP ALAGY ALMA_UNASSIGNED_HOLDINGS ALUQN ALVPJ AMBMR AMYDB ARCSS ASPBG ATUGU AUFTA AVWKF AZBYB AZFZN AZVAB BAFTC BDRZF BFHJK BHBCM BMNLL BMXJE BNHUX BROTX BRXPI BY8 CAG COF CS3 CWDTD D-E D-F DCZOG DPXWK DR2 DRFUL DRSTM DU5 EAD EAP EBA EBO EBR EBS EBU EDO EJD EMK EST ESX F00 F01 F04 F5P FEDTE FZ0 G-S G.N GODZA H.T H.X HF~ HGLYW HVGLF HZI HZ~ I-F IHE IX1 J0M K1G K48 LATKE LC2 LC3 LEEKS LH4 LITHE LOXES LP6 LP7 LUTES LW6 LYRES MEWTI MK4 MRFUL MRSTM MSFUL MSSTM MXFUL MXSTM N04 N05 N9A NF~ O66 O9- OIG P2W P2X P4D PALCI PQQKQ Q.N Q11 QB0 QWB R.K RDJ RIWAO RJQFR ROL RX1 SAMSI SUPJJ TH9 TN5 TUS UB1 V8K W8V W99 WBKPD WIH WIK WOHZO WQJ WXSBR WYISQ WZISG XG1 ZL0 ZZTAW ~IA ~IF ~WT AAYXX AIQQE CITATION O8X 7SC 8FD JQ2 L7M L~C L~D |
| ID | FETCH-LOGICAL-c3280-4c6bb1fc1f6ee05a914a2262226d7d730e80ccead931d25e9398820d62dd6a323 |
| IEDL.DBID | DRFUL |
| ISICitedReferencesCount | 0 |
| ISICitedReferencesURI | http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=001470166000001&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D |
| ISSN | 0167-7055 |
| IngestDate | Wed Aug 13 05:54:40 EDT 2025 Sat Nov 29 07:41:50 EST 2025 Mon Jul 21 09:51:54 EDT 2025 |
| IsDoiOpenAccess | false |
| IsOpenAccess | true |
| IsPeerReviewed | true |
| IsScholarly | true |
| Issue | 2 |
| Language | English |
| LinkModel | DirectLink |
| MergedId | FETCHMERGED-LOGICAL-c3280-4c6bb1fc1f6ee05a914a2262226d7d730e80ccead931d25e9398820d62dd6a323 |
| Notes | ObjectType-Article-1 SourceType-Scholarly Journals-1 ObjectType-Feature-2 content type line 14 |
| OpenAccessLink | https://onlinelibrary.wiley.com/doi/pdfdirect/10.1111/cgf.70070 |
| PQID | 3231791683 |
| PQPubID | 30877 |
| PageCount | 14 |
| ParticipantIDs | proquest_journals_3231791683 crossref_primary_10_1111_cgf_70070 wiley_primary_10_1111_cgf_70070_CGF70070 |
| PublicationCentury | 2000 |
| PublicationDate | May 2025 |
| PublicationDateYYYYMMDD | 2025-05-01 |
| PublicationDate_xml | – month: 05 year: 2025 text: May 2025 |
| PublicationDecade | 2020 |
| PublicationPlace | Oxford |
| PublicationPlace_xml | – name: Oxford |
| PublicationTitle | Computer graphics forum |
| PublicationYear | 2025 |
| Publisher | Blackwell Publishing Ltd |
| Publisher_xml | – name: Blackwell Publishing Ltd |
| References | 2019; 5 2210 2023; 37 2009 2023; 1 2020; 33 2024 2012; 31 2016; 35 2007; 29 2017; 30 2021; 34 2023 2022 2021 2020 2022; 13678 2018; 11218 2019 2018 2015 2211 2014; 7 2021; 40 2018; 31 e_1_2_7_5_2 e_1_2_7_3_2 e_1_2_7_9_2 e_1_2_7_7_2 e_1_2_7_19_2 e_1_2_7_15_2 e_1_2_7_60_2 e_1_2_7_13_2 e_1_2_7_41_2 e_1_2_7_62_2 e_1_2_7_43_2 e_1_2_7_64_2 e_1_2_7_45_2 e_1_2_7_47_2 e_1_2_7_26_2 e_1_2_7_26_3 e_1_2_7_28_2 Kulikov V. (e_1_2_7_25_2) 2023 Zhang K. (e_1_2_7_57_2) 2022 e_1_2_7_52_2 e_1_2_7_23_2 e_1_2_7_31_2 e_1_2_7_54_2 e_1_2_7_21_2 e_1_2_7_56_2 e_1_2_7_35_2 e_1_2_7_58_2 e_1_2_7_39_2 Ho J. (e_1_2_7_17_2) 2020 Nikankin Y. (e_1_2_7_34_2) 2023 e_1_2_7_4_2 e_1_2_7_2_2 e_1_2_7_8_2 e_1_2_7_6_2 e_1_2_7_18_2 e_1_2_7_16_2 e_1_2_7_61_2 e_1_2_7_14_2 e_1_2_7_40_2 e_1_2_7_63_2 e_1_2_7_42_2 e_1_2_7_65_2 e_1_2_7_10_2 e_1_2_7_44_2 Dhariwal P. (e_1_2_7_11_2) 2021 e_1_2_7_48_2 e_1_2_7_27_2 e_1_2_7_29_2 Vaswani A. (e_1_2_7_49_2) 2017 Gur S. (e_1_2_7_12_2) 2020 Rombach R. (e_1_2_7_37_2) 2022 Wang T.‐C. (e_1_2_7_50_2) 2018 Sohl‐Dickstein J. (e_1_2_7_46_2) 2015 Nichol A. Q. (e_1_2_7_33_2) 2021 e_1_2_7_24_2 e_1_2_7_30_2 e_1_2_7_51_2 e_1_2_7_22_2 e_1_2_7_32_2 e_1_2_7_53_2 e_1_2_7_20_2 e_1_2_7_55_2 e_1_2_7_36_2 e_1_2_7_38_2 e_1_2_7_59_2 |
| References_xml | – start-page: 14040 year: 2021 end-page: 14049 – volume: 5 start-page: 267 issue: 3 year: 2019 end-page: 291 article-title: Object removal from complex videos using a few annotations publication-title: Comput. Vis. Media – start-page: 9446 year: 2018 end-page: 9454 – start-page: 11461 year: 2022 end-page: 11471 – start-page: 23206 year: 2023 end-page: 23217 – start-page: 17920 year: 2023 end-page: 17930 article-title: SinDDM: A Single Image Denoising Diffusion Model – start-page: 14559 year: 2021 end-page: 14568 article-title: Internal Video Inpainting by Implicit Long‐range Propagation – start-page: 10684 year: 2022 end-page: 10695 article-title: High‐Resolution Image Synthesis With Latent Diffusion Models – volume: 40 start-page: 210:1 issue: 6 year: 2021 end-page: 210:12 article-title: Layered neural atlases for consistent video editing publication-title: ACM Transactions on Graphics – start-page: 1 year: 2022 end-page: 10 article-title: Palette: Image‐to‐Image Diffusion Models – year: 2021 – year: 2024 – volume: 35 start-page: 1 issue: 6 year: 2016 end-page: 11 article-title: Temporally coherent completion of dynamic video publication-title: ACM Transactions on Graphics – year: 2018 – start-page: 2720 year: 2019 end-page: 2729 article-title: An Internal Learning Approach to Video Inpainting – volume: 37 start-page: 9117 issue: 8 year: 2023 end-page: 9125 article-title: VIDM: Video Implicit Diffusion Models publication-title: Proceedings of the AAAI Conference on Artificial Intelligence – start-page: 7441 year: 2023 end-page: 7451 – volume: 1 start-page: 1795 year: 2023 end-page: 1803 article-title: Pyramid Diffusion Models for Low‐light Image Enhancement. In – volume: 33 start-page: 6840 year: 2020 end-page: 6851 article-title: Denoising Diffusion Probabilistic Models – start-page: 18456 year: 2023 end-page: 18466 – year: 2022 – start-page: 4569 year: 2019 end-page: 4579 article-title: SinGAN: Learning a Generative Model From a Single Natural Image – start-page: 6703 year: 2018 end-page: 6712 – start-page: 713 year: 2020 end-page: 729 article-title: Flow‐edge Guided Video Completion – volume: 31 start-page: 219 issue: 2pt1 year: 2012 end-page: 228 article-title: How Not to Be Seen — Object Removal from Videos of Crowded Scenes publication-title: Computer Graphics Forum – start-page: 60 end-page: 65 – volume: 13678 start-page: 74 year: 2022 end-page: 90 article-title: Flow‐Guided Transformer for Video Inpainting – start-page: 22563 year: 2023 end-page: 22575 – start-page: 17541 year: 2022 end-page: 17550 article-title: Towards An End‐to‐End Framework for Flow‐Guided Video Inpainting – start-page: 1 year: 2022 end-page: 21 – start-page: 3511 year: 2022 end-page: 3520 – start-page: 1 year: 2022 end-page: 14 – volume: 31 start-page: 1144 year: 2018 end-page: 1156 article-title: Video‐to‐Video Synthesis – start-page: 10443 year: 2023 end-page: 10452 article-title: ProPainter: Improving Propagation and Transformer for Video Inpainting – start-page: 23040 year: 2023 end-page: 23050 – start-page: 7162 year: 2024 end-page: 7172 article-title: AVID: Any‐Length Video Inpainting with Diffusion Model – start-page: 586 year: 2018 end-page: 595 article-title: The Unreasonable Effectiveness of Deep Features as a Perceptual Metric – start-page: 3190 year: 2023 end-page: 3199 article-title: Uni‐paint: A Unified Framework for Multimodal Image Inpainting with Pretrained Diffusion Model – start-page: 5982 year: 2022 end-page: 5991 – start-page: 22500 year: 2023 end-page: 22510 – start-page: 151 year: 2009 end-page: 158 – start-page: 6228 year: 2018 end-page: 6237 article-title: The Perception‐Distortion Tradeoff – year: 2211 – start-page: 8162 year: 2021 end-page: 8171 article-title: Improved Denoising Diffusion Probabilistic Models – start-page: 3741 year: 2021 end-page: 3752 article-title: Stochastic Image‐to‐Video Synthesis using ciNNs – start-page: 5792 year: 2019 end-page: 5801 – start-page: 74 year: 2022 end-page: 90 article-title: Flow‐guided transformer for video inpainting – start-page: 3718 year: 2019 end-page: 3727 – volume: 30 start-page: 5998 year: 2017 end-page: 6008 article-title: Attention is All you Need – volume: 11218 start-page: 334 year: 2018 end-page: 351 article-title: A New Large Scale Dynamic Texture Dataset with Application to ConvNet understanding – volume: 33 start-page: 16761 year: 2020 end-page: 16772 article-title: Hierarchical Patch VAE‐GAN: Generating Diverse Videos from a Single Sample – volume: 29 start-page: 463 issue: 3 year: 2007 end-page: 476 article-title: Space‐Time Completion of Video publication-title: IEEE Transactions on Pattern Analysis and Machine Intelligence – start-page: 2256 year: 2015 end-page: 2265 article-title: Deep Unsupervised Learning using Nonequilibrium Thermodynamics – volume: 7 start-page: 1993 issue: 4 year: 2014 end-page: 2019 article-title: Video Inpainting of Complex Scenes publication-title: SIAM Journal on Imaging Sciences – year: 2023 – year: 2210 – year: 2023 article-title: Sinfusion: Training diffusion models on a single image or video – volume: 34 start-page: 8780 year: 2021 end-page: 8794 article-title: Diffusion Models Beat GANs on Image Synthesis – ident: e_1_2_7_61_2 doi: 10.1109/ICCV51070.2023.00961 – ident: e_1_2_7_16_2 doi: 10.1109/ICCV51070.2023.00684 – ident: e_1_2_7_24_2 doi: 10.1109/CVPR.2019.00594 – ident: e_1_2_7_2_2 doi: 10.1109/CVPR.2005.38 – ident: e_1_2_7_30_2 doi: 10.1109/CVPR52688.2022.01704 – ident: e_1_2_7_52_2 doi: 10.1109/CVPR.2019.00384 – ident: e_1_2_7_55_2 doi: 10.1109/CVPR.2018.00577 – ident: e_1_2_7_59_2 doi: 10.1109/CVPR52688.2022.00589 – ident: e_1_2_7_47_2 doi: 10.1109/CVPR.2018.00701 – ident: e_1_2_7_53_2 doi: 10.1109/CVPR52729.2023.02148 – start-page: 8162 volume-title: Proceedings of the 38th International Conference on Machine Learning year: 2021 ident: e_1_2_7_33_2 – start-page: 1144 volume-title: Advances in Neural Information Processing Systems year: 2018 ident: e_1_2_7_50_2 – ident: e_1_2_7_13_2 doi: 10.1007/978‐3‐030‐58610‐2_42 – ident: e_1_2_7_15_2 – ident: e_1_2_7_36_2 doi: 10.1109/ICCV.2009.5459159 – ident: e_1_2_7_7_2 doi: 10.1109/CVPR52729.2023.02161 – ident: e_1_2_7_62_2 doi: 10.1109/ICCV.2019.00281 – ident: e_1_2_7_45_2 – volume-title: International Conference on Machine Learning year: 2023 ident: e_1_2_7_34_2 – ident: e_1_2_7_42_2 – ident: e_1_2_7_60_2 doi: 10.1109/CVPR.2018.00068 – ident: e_1_2_7_63_2 doi: 10.1109/CVPR52733.2024.00684 – ident: e_1_2_7_32_2 doi: 10.1137/140954933 – ident: e_1_2_7_39_2 doi: 10.1109/CVPR52688.2022.00350 – ident: e_1_2_7_23_2 doi: 10.1145/3478513.3480546 – ident: e_1_2_7_8_2 doi: 10.1109/ICCV51070.2023.02106 – ident: e_1_2_7_26_3 – start-page: 8780 volume-title: Advances in Neural Information Processing Systems year: 2021 ident: e_1_2_7_11_2 – ident: e_1_2_7_43_2 doi: 10.1109/TPAMI.2022.3204461 – ident: e_1_2_7_5_2 – ident: e_1_2_7_9_2 doi: 10.1109/ICCV51070.2023.02121 – start-page: 10684 volume-title: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition year: 2022 ident: e_1_2_7_37_2 – start-page: 5998 volume-title: Advances in Neural Information Processing Systems year: 2017 ident: e_1_2_7_49_2 – ident: e_1_2_7_35_2 doi: 10.1109/ICCV48922.2021.01431 – ident: e_1_2_7_19_2 – ident: e_1_2_7_21_2 doi: 10.1007/978‐3‐030‐01264‐9_20 – ident: e_1_2_7_27_2 – ident: e_1_2_7_29_2 doi: 10.1109/CVPR52688.2022.01117 – ident: e_1_2_7_58_2 doi: 10.1007/978‐3‐031‐19797‐0_5 – start-page: 16761 volume-title: Advances in Neural Information Processing Systems year: 2020 ident: e_1_2_7_12_2 – ident: e_1_2_7_10_2 doi: 10.1109/CVPR46437.2021.00374 – ident: e_1_2_7_40_2 doi: 10.1145/3528233.3530757 – ident: e_1_2_7_41_2 doi: 10.1109/ICCV.2019.00467 – ident: e_1_2_7_6_2 – start-page: 17920 volume-title: Proceedings of the 40th International Conference on Machine Learning year: 2023 ident: e_1_2_7_25_2 – ident: e_1_2_7_18_2 doi: 10.1145/2980179.2982398 – ident: e_1_2_7_65_2 – ident: e_1_2_7_20_2 – ident: e_1_2_7_14_2 doi: 10.1111/j.1467-8659.2012.03000.x – ident: e_1_2_7_38_2 doi: 10.1109/CVPR52729.2023.02155 – ident: e_1_2_7_54_2 doi: 10.1145/3581783.3612200 – ident: e_1_2_7_4_2 doi: 10.1109/CVPR.2018.00652 – ident: e_1_2_7_31_2 doi: 10.1609/aaai.v37i8.26094 – ident: e_1_2_7_64_2 doi: 10.24963/ijcai.2023/199 – ident: e_1_2_7_56_2 doi: 10.1109/CVPR52729.2023.01770 – ident: e_1_2_7_48_2 doi: 10.1109/CVPR.2018.00984 – ident: e_1_2_7_3_2 – start-page: 6840 volume-title: Advances in Neural Information Processing Systems year: 2020 ident: e_1_2_7_17_2 – start-page: 2256 volume-title: Proceedings of the 32nd International Conference on Machine Learning year: 2015 ident: e_1_2_7_46_2 – ident: e_1_2_7_22_2 – start-page: 74 volume-title: European Conference on Computer Vision year: 2022 ident: e_1_2_7_57_2 – ident: e_1_2_7_28_2 doi: 10.1109/ICCV48922.2021.01378 – ident: e_1_2_7_26_2 doi: 10.1007/s41095-019-0145-0 – ident: e_1_2_7_51_2 doi: 10.1109/TPAMI.2007.60 – ident: e_1_2_7_44_2 |
| SSID | ssj0004765 |
| Score | 2.4346557 |
| Snippet | Video inpainting is the task of filling a region in a video in a visually convincing manner It is very challenging due to the high dimensionality of the data... |
| SourceID | proquest crossref wiley |
| SourceType | Aggregation Database Index Database Publisher |
| SubjectTerms | CCS Concepts Computing methodologies → Image processing Diffusion models Inference Learning Noise levels Parameters Video |
| Title | Infusion: Internal Diffusion for Inpainting of Dynamic Textures and Complex Motion |
| URI | https://onlinelibrary.wiley.com/doi/abs/10.1111%2Fcgf.70070 https://www.proquest.com/docview/3231791683 |
| Volume | 44 |
| WOSCitedRecordID | wos001470166000001&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D |
| hasFullText | 1 |
| inHoldings | 1 |
| isFullTextHit | |
| isPrint | |
| journalDatabaseRights | – providerCode: PRVWIB databaseName: Wiley Online Library Full Collection 2020 customDbUrl: eissn: 1467-8659 dateEnd: 99991231 omitProxy: false ssIdentifier: ssj0004765 issn: 0167-7055 databaseCode: DRFUL dateStart: 19970101 isFulltext: true titleUrlDefault: https://onlinelibrary.wiley.com providerName: Wiley-Blackwell |
| link | http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwpV1NS8NAEB1q60EPfovVKot48BJJsskm0ZO0RoUqUqp4C-nORgolLf0Qf76zm0TrQRC8hSXZhMm8mbfD7huAMyeTnkAvtCjXouX5ijDnRNLKeGajy6WDRkvvpRs8Poavr9FTDa6qszCFPsRXwU0jw8RrDfB0MFsCuXzLLgKtVrMCDZf81qtDo9OLn7vfxyID4VfS3lo0phQW0ht5vh7-mY6-OeYyUzWpJt7810duwUbJMNl14RLbUFP5Dqwv6Q7uQu8-zxa6THbJyorgiHWGWTHGiMbS8CQdmiYSbJyxTtG2nvUpki9ofc7SHJmOJCP1wR5MH6A9eI5v-u07q2yuYEnuhrblSTEY0J9yMqGU7aeR46VExYguCAyQcK9CW0rys4g76Poq4hGRcRuFiyhS7vJ9qOfjXB0AQ6KIwvdpqkB6aGM44MhDz0eFtkhV2oTTysbJpNDQSKq1BxkoMQZqQquyflLCaJbQa7R8qgh5E86NnX-fIGnfxubi8O-3HsGaq_v5mg2MLajPpwt1DKvyfT6cTU9Kf_oEOEjM-A |
| linkProvider | Wiley-Blackwell |
| linkToHtml | http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwpV1NS8NAEB1qFdSD32L9XMSDl0iSTTaJeJHW2mItIlV6C-nORgolSmvFn-_sJqn1IAjewpJswmTezNth9w3AmZNKT6AXWpRr0fJ8RZhzImmlPLXR5dJBo6X33Am63bDfjx4qcFWehcn1IWYFN40ME681wHVBeg7l8iW9CLRczQIseuRGfhUWG4_Np873uchA-KW2t1aNKZSF9E6e2cM_89E3yZynqibXNNf_95UbsFZwTHadO8UmVFS2BatzyoPb8NjO0qkulF2yoiY4Yo1hmo8xIrI0_JYMTRsJ9pqyRt64nvUolk9phc6SDJmOJSP1ye5NJ6AdeGre9Ootq2ivYEnuhrblSTEY0L9yUqGU7SeR4yVExogwCAyQkK9CW0rytIg76Poq4hHRcRuFiygS7vJdqGavmdoDhkQShe_TVIH00MZwwJGHno8KbZGopAanpZHjt1xFIy5XH2Sg2BioBoel-eMCSJOYXqMFVEXIa3BuDP37BHH9tmku9v9-6wkst3r3nbjT7t4dwIqru_ua7YyHUH0fT9URLMmP9-FkfFw41xeLVNDo |
| linkToPdf | http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwpV1LS8QwEB58IXrwLa7PIB68VNqmTVvxIq5VcV2WZRVvpZtJZEHqoq74852krbseBMFbCW1apvPNfBmSbwCOPC0DgUHsUK5FJwgVYc5LpKO5dtHn0kOrpffQitrt-PEx6UzBWX0WptSH-C64GWTYeG0AroaoJ1Aun_RJZORqpmE2CBNBsJxtdtP71vhcZCTCWtvbqMZUykJmJ8_3wz_z0ZhkTlJVm2vS5f995QosVRyTnZdOsQpTqliDxQnlwXXo3hR6ZAplp6yqCT6z5kCXY4yILA0P84FtI8FeNGuWjetZj2L5iFboLC-QmVjyrD7Zne0EtAH36WXv4tqp2is4kvux6wRS9Pv0rzwtlHLDPPGCnMgYEQaBERLyVexKSZ6WcA_9UCU8ITruovARRc59vgkzxUuhtoAhkUQRhjRVJAN0Me5z5HEQokJX5CpvwGFt5GxYqmhk9eqDDJRZAzVgtzZ_VgHpLaPXGAFVEfMGHFtD_z5BdnGV2ovtv996APOdZpq1btq3O7Dgm-a-djfjLsy8v47UHszJj_fB2-t-5VtfW1PQYw |
| openUrl | ctx_ver=Z39.88-2004&ctx_enc=info%3Aofi%2Fenc%3AUTF-8&rfr_id=info%3Asid%2Fsummon.serialssolutions.com&rft_val_fmt=info%3Aofi%2Ffmt%3Akev%3Amtx%3Ajournal&rft.genre=article&rft.atitle=Infusion%3A+Internal+Diffusion+for+Inpainting+of+Dynamic+Textures+and+Complex+Motion&rft.jtitle=Computer+graphics+forum&rft.au=Cherel%2C+N.&rft.au=Almansa%2C+A.&rft.au=Gousseau%2C+Y.&rft.au=Newson%2C+A.&rft.date=2025-05-01&rft.issn=0167-7055&rft.eissn=1467-8659&rft.volume=44&rft.issue=2&rft.epage=n%2Fa&rft_id=info:doi/10.1111%2Fcgf.70070&rft.externalDBID=10.1111%252Fcgf.70070&rft.externalDocID=CGF70070 |
| thumbnail_l | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=0167-7055&client=summon |
| thumbnail_m | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=0167-7055&client=summon |
| thumbnail_s | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=0167-7055&client=summon |