11.14.3.9.1 Image Composition, Video Composition

Chapter Contents (Back)
Composition. Image Composition. Video Composition.
See also Image Matting, Video Matting. Generally only an object:
See also Merging Views, Object Insertion in Image. A lot of overlap:
See also Image Editing, Interactive Editing, Image Manipulation.

Ahmad, S.[Subutai],
Method and apparatus for model-based compositing,
US_Patent6,532,022, Mar 11, 2003
WWW Link. BibRef 0303

Minami, N.[Nobuyuki], Kurashige, M.[Masafumi],
Video signal processing device and method employingtransformation matrix to generate composite image,
US_Patent6,441,864, Aug 27, 2002
WWW Link. BibRef 0208

Tlaskal, M.P.[Martin Paul], Long, T.M.[Timothy Merrick],
Optimising image compositing,
US_Patent6,816,619, Nov 9, 2004
WWW Link. BibRef 0411

Tiana, C.[Carlo],
Image fusion system and method,
US_Patent6,898,331, May 24, 2005
WWW Link. More compositing than fusion. BibRef 0505

White, M.S.[Marvin S.], Honey, S.K.[Stanley K.], Hsiao, W.[Walter], Gloudemans, J.R.[James R.], Meier, K.R.[Kevin R.], McGuffin, J.[James], Cavallaro, R.H.[Richard H.],
Video compositor,
US_Patent6,909,438, Jun 21, 2005
WWW Link. BibRef 0506

Xie, Z.F.[Zhi-Feng], Shen, Y.[Yang], Ma, L.Z.[Li-Zhuang], Chen, Z.H.[Zhi-Hua],
Seamless video composition using optimized mean-value cloning,
VC(26), No. 6-8, June 2010, pp. 1123-1134.
WWW Link. 1101
BibRef

Wen, J., Zhang, B., Pan, C., Zhang, X.,
Image composition by constraining responses of filters,
IET-IPR(6), No. 1, 2012, pp. 11-21.
DOI Link 1202
For: face data illumination removal, remote-sensing images fusion, texture transfer, multi-focus image fusion, seamless texture tiling. BibRef

Chen, T.[Tao], Zhu, J.Y.[Jun-Yan], Shamir, A., Hu, S.M.[Shi-Min],
Motion-Aware Gradient Domain Video Composition,
IP(22), No. 7, 2013, pp. 2532-2544.
IEEE DOI 1307
image motion analysis; user interfaces; human eye; video editing BibRef

Park, T.[Taesung], Liu, M.Y.[Ming-Yu], Wang, T.C.[Ting-Chun], Zhu, J.Y.[Jun-Yan],
Semantic Image Synthesis With Spatially-Adaptive Normalization,
CVPR19(2332-2341).
IEEE DOI 2002
BibRef

Ni, B., Xu, M., Cheng, B., Wang, M., Yan, S., Tian, Q.,
Learning to Photograph: A Compositional Perspective,
MultMed(15), No. 5, 2013, pp. 1138-1151.
IEEE DOI 1307
Computational modeling BibRef

Wang, P.[Pan], Cheng, Z.Q.[Zhi-Quan], Martin, R.[Ralph], Liu, H.H.[Hua-Hai], Cai, X.[Xun], Li, S.[Sikun],
NUMA-aware image compositing on multi-GPU platform,
VC(29), No. 6-8, June 2013, pp. 639-649.
WWW Link. 1306
BibRef

Wang, W., Xu, P., Bie, X.H.[Xiao-Hui], Hua, M.[Miao],
Enhanced Use of Mattes for Easy Image Composition,
IP(25), No. 10, October 2016, pp. 4608-4616.
IEEE DOI 1610
image enhancement BibRef

Wu, H.[Hao], Li, Y.L.[Yue-Li], Miao, Z.J.[Zhen-Jiang], Wang, Y.Q.[Yu-Qi], Zhu, R.S.[Run-Sheng], Bie, R.F.[Rong-Fang], Wang, Y.[Yi],
Creative and high-quality image composition based on a new criterion,
JVCIR(38), No. 1, 2016, pp. 100-114.
Elsevier DOI 1605
Image composition BibRef

Wang, J., Sheng, B., Li, P., Jin, Y., Feng, D.D.,
Illumination-Guided Video Composition via Gradient Consistency Optimization,
IP(28), No. 10, October 2019, pp. 5077-5090.
IEEE DOI 1909
Lighting, Cloning, Image color analysis, Interpolation, Optical imaging, Smoothing methods, Optical mixing, video composition BibRef

An, S., Liu, S., Huang, Z., Che, G., Bao, Q., Zhu, Z., Chen, Y., Weng, D.Z.,
RotateView: A Video Composition System for Interactive Product Display,
MultMed(21), No. 12, December 2019, pp. 3095-3105.
IEEE DOI 1912
Optical imaging, Mobile handsets, Object segmentation, Image color analysis, Motion segmentation, Image segmentation, video composition BibRef

Francini, S.[Saverio], Hermosilla, T.[Txomin], Coops, N.C.[Nicholas C.], Wulder, M.A.[Michael A.], White, J.C.[Joanne C.], Chirici, G.[Gherardo],
An assessment approach for pixel-based image composites,
PandRS(202), 2023, pp. 1-12.
Elsevier DOI 2308
Cloud-free composites, BAP, Medoid, Remote Sensing, Landsat BibRef

Khaleghi, M.M.[Mir Mohammad], Safayani, M.[Mehran], Mirzaei, A.[Abdolreza],
GraPLUS: Graph-based Placement Using Semantics for image composition,
CVIU(259), 2025, pp. 104427.
Elsevier DOI 2509
Object placement, Scene graphs, Language models, Graph neural networks, Image composition, Attention mechanism BibRef

Huang, K.Y.[Kai-Yi], Duan, C.Q.[Cheng-Qi], Sun, K.Y.[Kai-Yue], Xie, E.[Enze], Li, Z.G.[Zhen-Guo], Liu, X.H.[Xi-Hui],
T2I-CompBench++: An Enhanced and Comprehensive Benchmark for Compositional Text-to-Image Generation,
PAMI(47), No. 5, May 2025, pp. 3563-3579.
IEEE DOI 2504
Text to image, Benchmark testing, Measurement, Image color analysis, Shape, Marine vehicles, Layout, image generation BibRef

Cong, Y.[Yuren], Min, M.R.Q.[Martin Ren-Qiang], Li, L.E.[Li Erran], Rosenhahn, B.[Bodo], Yang, M.Y.[Michael Ying],
Attribute-Centric Compositional Text-to-Image Generation,
IJCV(133), No. 7, July 2025, pp. 4555-4570.
Springer DOI 2506
BibRef

Cong, Y.[Yuren], Yi, J.H.[Jin-Hui], Rosenhahn, B.[Bodo], Yang, M.Y.[Michael Ying],
SSGVS: Semantic Scene Graph-to-Video Synthesis,
MULA23(2555-2565)
IEEE DOI 2309
BibRef

Liu, S.Y.[Sheng-Yuan], Wang, B.[Bo], Ma, Y.[Ye], Yang, T.[Te], Chen, Q.[Quan], Dong, D.[Di],
Training-free subject-enhanced attention guidance for compositional text-to-image generation,
PR(170), 2026, pp. 112111.
Elsevier DOI 2509
Subject-driven generation, Compositional generation, Diffusion model BibRef


Feng, W.X.[Wei-Xi], Liu, C.[Chao], Liu, S.[Sifei], Wang, W.Y.[William Yang], Vahdat, A.[Arash], Nie, W.[Weili],
BlobGEN-Vid: Compositional Text-to-Video Generation with Blob Video Representations,
CVPR25(12989-12998)
IEEE DOI 2508
Visualization, Semantics, Layout, Diffusion models, Controllability, Generators, Planning, Text to video, text-to-video generation, controllable video generation BibRef

Ge, C.J.[Chong-Jian], Xu, C.F.[Chen-Feng], Ji, Y.F.[Yuan-Feng], Peng, C.S.[Chen-Sheng], Tomizuka, M.[Masayoshi], Luo, P.[Ping], Ding, M.Y.[Ming-Yu], Jampani, V.[Varun], Zhan, W.[Wei],
COMPGS: Unleashing 2D Compositionality for Compositional Text-to-3D via Dynamically Optimizing 3D Gaussians,
CVPR25(18509-18520)
IEEE DOI 2508
Image quality, Image synthesis, Semantics, Optimization, 3d generation, gaussian splatting BibRef

Li, M.C.[Ming-Cheng], Hou, X.L.[Xiao-Lu], Liu, Z.Y.[Zi-Yang], Yang, D.K.[Ding-Kang], Qian, Z.Y.[Zi-Yun], Chen, J.W.[Jia-Wei], Wei, J.J.[Jin-Jie], Jiang, Y.[Yue], Xu, Q.Y.[Qing-Yao], Zhang, L.H.[Li-Hua],
MCCD: Multi-Agent Collaboration-based Compositional Diffusion for Complex Text-to-Image Generation,
CVPR25(13263-13272)
IEEE DOI 2508
Accuracy, Filtering, Text to image, Diffusion models, text-to-image generation, large language modeling, diffusion modeling BibRef

Tarrés, G.C.[Gemma Canet], Lin, Z.[Zhe], Zhang, Z.F.[Zhi-Fei], Zhang, H.[He], Gilbert, A.[Andrew], Collomosse, J.[John], Kim, S.Y.[Soo Ye],
Multitwine: Multi-Object Compositing with Text and Layout Control,
CVPR25(8094-8104)
IEEE DOI 2508
Training, Visualization, Computational modeling, Layout, Pipelines, Training data, Data collection, Data models BibRef

Qu, L.G.[Lei-Gang], Li, H.C.[Hao-Chuan], Wang, W.J.[Wen-Jie], Liu, X.[Xiang], Li, J.C.[Jun-Cheng], Nie, L.Q.[Li-Qiang], Chua, T.S.[Tat-Seng],
SILMM: Self-Improving Large Multimodal Models for Compositional Text-to-Image Generation,
CVPR25(18497-18508)
IEEE DOI Code:
WWW Link. 2508
Visualization, Limiting, Scalability, Text to image, Image representation, Planning, Iterative methods, self-improvement BibRef

Hong, Y.[Yan], Duan, Y.X.[Yu-Xuan], Zhang, B.[Bo], Chen, H.X.[Hao-Xing], Lan, J.[Jun], Zhu, H.[Huijia], Wang, W.Q.[Wei-Qiang], Zhang, J.[Jianfu],
Comfusion: Enhancing Personalized Generation by Instance-scene Compositing and Fusion,
ECCV24(XLIV: 1-18).
Springer DOI 2412
Personalized. BibRef

Chen, Z.K.[Zhe-Kai], Wang, W.[Wen], Yang, Z.[Zhen], Yuan, Z.[Zeqing], Chen, H.[Hao], Shen, C.H.[Chun-Hua],
Freecompose: Generic Zero-Shot Image Composition with Diffusion Prior,
ECCV24(XVII: 70-87).
Springer DOI 2412
BibRef

Wang, L.Z.[Luo-Zhou], Shen, G.B.[Gui-Bao], Ge, W.H.[Wen-Hang], Chen, G.Y.[Guang-Yong], Li, Y.J.[Yi-Jun], Chen, Y.C.[Ying-Cong],
Text-anchored Score Composition: Tackling Condition Misalignment in Text-to-image Diffusion Models,
ECCV24(XLVII: 21-37).
Springer DOI 2412
BibRef

Wang, Z.[Zirui], Sha, Z.Z.[Zhi-Zhou], Ding, Z.[Zheng], Wang, Y.L.[Yi-Lin], Tu, Z.W.[Zhuo-Wen],
TokenCompose: Text-to-Image Diffusion with Token-Level Supervision,
CVPR24(8553-8564)
IEEE DOI 2410
Training, Photorealism, Pipelines, Noise reduction, Text to image, Object segmentation, Benchmark testing, Diffusion Models, Compositional Generation BibRef

Liu, J.Q.[Jia-Qi], Huang, T.[Tao], Xu, C.[Chang],
Training-free Composite Scene Generation for Layout-to-image Synthesis,
ECCV24(LXVIII: 37-53).
Springer DOI 2412
BibRef

Wang, Q.[Qi], Lu, R.J.[Rui-Jie], Xu, X.D.[Xu-Dong], Wang, J.B.[Jing-Bo], Wang, M.Y.[Michael Yu], Dai, B.[Bo], Zeng, G.[Gang], Xu, D.[Dan],
Roomtex: Texturing Compositional Indoor Scenes via Iterative Inpainting,
ECCV24(LXVIII: 465-482).
Springer DOI 2412
BibRef

Ding, G.G.[Gang-Gui], Zhao, C.[Canyu], Wang, W.[Wen], Yang, Z.[Zhen], Liu, Z.[Zide], Chen, H.[Hao], Shen, C.H.[Chun-Hua],
FreeCustom: Tuning-Free Customized Image Generation for Multi-Concept Composition,
CVPR24(9089-9098)
IEEE DOI 2410
Training, Codes, Image synthesis, Text to image, Faces, image customization, diffusion model, generative model BibRef

Chen, R.D.[Rui-Dong], Wang, L.[Lanjun], Nie, W.Z.[Wei-Zhi], Zhang, Y.D.[Yong-Dong], Liu, A.A.[An-An],
AnyScene: Customized Image Synthesis with Composited Foreground,
CVPR24(8724-8733)
IEEE DOI 2410
Measurement, Visualization, Image synthesis, Semantics, Layout, Text to image, text to image generation, generative model BibRef

Burgert, R.D.[Ryan D.], Price, B.L.[Brian L.], Kuen, J.[Jason], Li, Y.J.[Yi-Jun], Ryoo, M.S.[Michael S.],
MAGICK: A Large-Scale Captioned Dataset from Matting Generated Images Using Chroma Keying,
CVPR24(22595-22604)
IEEE DOI Code:
WWW Link. 2410
Training, Hair, Image segmentation, Accuracy, Image synthesis, Text to image, alpha, matting, dataset, generation, text, image, compositing BibRef

Li, B.[Baiqi], Lin, Z.Q.[Zhi-Qiu], Pathak, D.[Deepak], Li, J.Y.[Jia-Yao], Fei, Y.X.[Yi-Xin], Wu, K.[Kewen], Xia, X.[Xide], Zhang, P.C.[Peng-Chuan], Neubig, G.[Graham], Ramanan, D.[Deva],
Evaluating and Improving Compositional Text-to-Visual Generation,
GenerativeFM24(5290-5301)
IEEE DOI 2410
Measurement, Visualization, Toxicology, Closed box, Footwear, Cognition BibRef

Lin, Z.Q.[Zhi-Qiu], Pathak, D.[Deepak], Li, B.[Baiqi], Li, J.Y.[Jia-Yao], Xia, X.[Xide], Neubig, G.[Graham], Zhang, P.[Pengchuan], Ramanan, D.[Deva],
Evaluating Text-to-visual Generation with Image-to-text Generation,
ECCV24(IX: 366-384).
Springer DOI 2412
BibRef

Wang, C.[Chao],
A Diffusion-Based Method for Multi-Turn Compositional Image Generation,
VAQuality24(374-384)
IEEE DOI 2404
Image synthesis, Fuses, Noise reduction, Semantics, Logic gates, Multitasking BibRef

Mehl, L.[Lukas], Bruhn, A.[Andrés], Gross, M.[Markus], Schroers, C.[Christopher],
Stereo Conversion with Disparity-Aware Warping, Compositing and Inpainting,
WACV24(4248-4257)
IEEE DOI 2404
Visualization, Solid modeling, Systematics, Production, Manuals, Algorithms, Computational photography, image and video synthesis, 3D computer vision BibRef

Liu, X.Y.[Xiao-Yu], Liu, M.[Ming], Li, J.[Junyi], Liu, S.[Shuai], Wang, X.T.[Xiao-Tao], Lei, L.[Lei], Zuo, W.M.[Wang-Meng],
Beyond Image Borders: Learning Feature Extrapolation for Unbounded Image Composition,
ICCV23(12977-12986)
IEEE DOI Code:
WWW Link. 2401
BibRef

Lu, S.L.[Shi-Lin], Liu, Y.Z.[Yan-Zhu], Kong, A.W.K.[Adams Wai-Kin],
TF-ICON: Diffusion-Based Training-Free Cross-Domain Image Composition,
ICCV23(2294-2305)
IEEE DOI Code:
WWW Link. 2401
BibRef

Liu, N.[Nan], Du, Y.L.[Yi-Lun], Li, S.[Shuang], Tenenbaum, J.B.[Joshua B.], Torralba, A.[Antonio],
Unsupervised Compositional Concepts Discovery with Text-to-Image Generative Models,
ICCV23(2085-2095)
IEEE DOI 2401
BibRef

Bahmani, S.[Sherwin], Park, J.J.[Jeong Joon], Paschalidou, D.[Despoina], Yan, X.G.[Xing-Guang], Wetzstein, G.[Gordon], Guibas, L.J.[Leonidas J.], Tagliasacchi, A.[Andrea],
CC3D: Layout-Conditioned Generation of Compositional 3D Scenes,
ICCV23(7137-7147)
IEEE DOI 2401
BibRef

Ku, W.F.[Wing-Fung], Siu, W.C.[Wan-Chi], Cheng, X.[Xi], Chan, H.A.[H. Anthony],
Intelligent Painter: Picture Composition with Resampling Diffusion Model,
ICIP23(2255-2259)
IEEE DOI 2312
BibRef

Shi, C.H.[Chang-Hao], Ni, H.[Haomiao], Li, K.[Kai], Han, S.B.[Shao-Bo], Liang, M.F.[Ming-Fu], Min, M.R.[Martin Renqiang],
Exploring Compositional Visual Generation with Latent Classifier Guidance,
GCV23(853-862)
IEEE DOI 2309
BibRef

Sheng, Y.C.[Yi-Chen], Zhang, J.M.[Jian-Ming], Philip, J.[Julien], Hold-Geoffroy, Y.[Yannick], Sun, X.[Xin], Zhang, H.[He], Ling, L.[Lu], Benes, B.[Bedrich],
PixHt-Lab: Pixel Height Based Light Effect Generation for Image Compositing,
CVPR23(16643-16653)
IEEE DOI 2309
BibRef

Zhu, S.[Sijie], Lin, Z.[Zhe], Cohen, S.[Scott], Kuen, J.[Jason], Zhang, Z.F.[Zhi-Fei], Chen, C.[Chen],
TopNet: Transformer-Based Object Placement Network for Image Compositing,
CVPR23(1838-1847)
IEEE DOI 2309
BibRef

Zhu, S.[Sijie], Lin, Z.[Zhe], Cohen, S.[Scott], Kuen, J.[Jason], Zhang, Z.F.[Zhi-Fei], Chen, C.[Chen],
GALA: Toward Geometry-and-Lighting-Aware Object Search for Compositing,
ECCV22(XXVII:676-692).
Springer DOI 2211
BibRef

Liu, N.[Nan], Li, S.[Shuang], Du, Y.L.[Yi-Lun], Torralba, A.[Antonio], Tenenbaum, J.B.[Joshua B.],
Compositional Visual Generation with Composable Diffusion Models,
ECCV22(XVII:423-439).
Springer DOI 2211
BibRef

Sheng, Y.C.[Yi-Chen], Zhang, J.M.[Jian-Ming], Benes, B.[Bedrich],
SSN: Soft Shadow Network for Image Compositing,
CVPR21(4378-4388)
IEEE DOI 2111
Training, Solid modeling, Visualization, Pipelines, Training data, Data models BibRef

Zhang, H.[He], Zhang, J.M.[Jian-Ming], Perazzi, F.[Federico], Lin, Z.[Zhe], Patel, V.M.[Vishal M.],
Deep Image Compositing,
WACV21(365-374)
IEEE DOI 2106
Image segmentation, Laplace equations, Image color analysis, Fuses, Decontamination, Training data BibRef

Zhan, F.N.[Fang-Neng], Lu, S.J.[Shi-Jian], Zhang, C.G.[Chang-Gong], Ma, F.Y.[Fei-Ying], Xie, X.S.[Xuan-Song],
Adversarial Image Composition with Auxiliary Illumination,
ACCV20(II:234-250).
Springer DOI 2103
BibRef

Li, Y.C.[Yun-Chang], Huang, Z.J.[Zhi-Jie], Sun, J.[Jun],
An Efficient Encoding Method for Video Compositing in HEVC,
MMMod20(I:65-76).
Springer DOI 2003
BibRef

Hu, G., Clark, J.,
Instance Segmentation Based Semantic Matting for Compositing Applications,
CRV19(135-142)
IEEE DOI 1908
Image segmentation, Semantics, Object segmentation, Pipelines, Task analysis, Learning systems, Estimation, compositing, instance segmentation BibRef

Tan, F.[Fuwen], Feng, S.[Song], Ordonez, V.[Vicente],
Text2Scene: Generating Compositional Scenes From Textual Descriptions,
CVPR19(6703-6712).
IEEE DOI 2002
BibRef

Zhao, H.S.[Heng-Shuang], Shen, X.H.[Xiao-Hui], Lin, Z.[Zhe], Sunkavalli, K.[Kalyan], Price, B.L.[Brian L.], Jia, J.Y.[Jia-Ya],
Compositing-Aware Image Search,
ECCV18(III: 517-532).
Springer DOI 1810
BibRef

Lin, C., Yumer, M.E.[M. Ersin], Wang, O., Shechtman, E., Lucey, S.,
ST-GAN: Spatial Transformer Generative Adversarial Networks for Image Compositing,
CVPR18(9455-9464)
IEEE DOI 1812
Training, Generators, Image generation, Manifolds, Generative adversarial networks, Games BibRef

Wang, Y., Zhong, F., Sun, X., Qin, X.,
Realistic image composite with best-buddy prior of natural image patches,
ICIP17(2274-2278)
IEEE DOI 1803
Density functional theory, Feature extraction, Histograms, Image color analysis, Image segmentation, Semantics, Image Composite BibRef

de Albuquerque Azevedo, R.G., Lima, G.F.,
A graphics composition architecture for multimedia applications based on layered-depth-image,
3DTV-CON16(1-4)
IEEE DOI 1610
computer graphics BibRef

Chalmers, A., Choi, J.J.[Jong Jin], Rhee, T.[Taehyun],
Perceptually based radiance map for realistic composition,
IVCNZ13(172-177)
IEEE DOI 1402
image processing BibRef

Park, J.[Jaesik], Lee, J.Y.[Joon-Young], Tai, Y.W.[Yu-Wing], Kweon, I.S.[In So],
Modeling photo composition and its application to photo re-arrangement,
ICIP12(2741-2744).
IEEE DOI 1302
BibRef

Schnyder, L.[Lars], Lang, M.[Manuel], Wang, O.[Oliver], Smolic, A.[Aljoscha],
Depth image based compositing for stereo 3D,
3DTV12(1-4).
IEEE DOI 1212
BibRef

Wang, D.[Dong], Jia, W.J.[Wei-Jia], Li, G.Q.[Gui-Qing], Xiong, Y.H.[Yun-Hui],
Natural Image Composition with Inhomogeneous Boundaries,
PSIVT11(II: 92-103).
Springer DOI 1111
BibRef

Pritch, Y.[Yael], Poleg, Y.[Yair], Peleg, S.[Shmuel],
Snap Image Composition,
MIRAGE11(181-191).
Springer DOI 1110
Compositing images with different backgrounds. BibRef

Hyun, M.H.[Myung-Han], Kim, S.Y.[Sung-Yeol], Ho, Y.S.[Yo-Sung],
Multi-View Image Matting and Compositing Using Trimap Sharing for Natural 3-D Scene Generation,
3DTV08(397-400).
IEEE DOI 0805
BibRef

Chapter on 3-D Object Description and Computation Techniques, Surfaces, Deformable, View Generation, Video Conferencing continues in
Inpainting, Filling Holes, Fixing Problems .


Last update:Sep 27, 2025 at 16:28:57