{ "table_of_contents": [ { "title": "Diffusion Models, Image Super-Resolution, and\nEverything: A Survey", "heading_level": null, "page_id": 0, "polygon": [ [ 69.79280054569244, 60.1148681640625 ], [ 541.9733934402466, 60.1148681640625 ], [ 541.9733934402466, 111.9208984375 ], [ 69.79280054569244, 111.9208984375 ] ] }, { "title": "I. INTRODUCTION", "heading_level": null, "page_id": 0, "polygon": [ [ 135.614990234375, 423.0916028022766 ], [ 214.22498381137848, 423.0916028022766 ], [ 213.36607360839844, 433.4482727050781 ], [ 135.4609740972519, 433.4482727050781 ] ] }, { "title": "II. IMAGE SR", "heading_level": null, "page_id": 1, "polygon": [ [ 141.93112099170685, 414.9322204589844 ], [ 204.58113777637482, 413.70578956604004 ], [ 204.58113777637482, 424.8952331542969 ], [ 141.93112099170685, 424.8952331542969 ] ] }, { "title": "A. Datasets", "heading_level": null, "page_id": 1, "polygon": [ [ 311.49005484580994, 232.2384033203125 ], [ 359.4068298339844, 232.2384033203125 ], [ 359.4068298339844, 242.201416015625 ], [ 311.49005484580994, 243.211656332016 ] ] }, { "title": "B. SR Models", "heading_level": null, "page_id": 1, "polygon": [ [ 311.05917620658875, 592.3551788330078 ], [ 369.1831433773041, 591.7547936439514 ], [ 369.1831433773041, 602.3181915283203 ], [ 311.05917620658875, 602.3181915283203 ] ] }, { "title": "C. Image Quality Assessment", "heading_level": null, "page_id": 2, "polygon": [ [ 311.57472038269043, 183.93524169921875 ], [ 432.0381774902344, 183.93524169921875 ], [ 432.0381774902344, 194.35737562179565 ], [ 311.57472038269043, 194.35737562179565 ] ] }, { "title": "III. DMS BASICS", "heading_level": null, "page_id": 3, "polygon": [ [ 399.54560565948486, 385.8891906738281 ], [ 475.1385192871094, 385.8891906738281 ], [ 475.1385192871094, 395.8522033691406 ], [ 399.54560565948486, 395.8522033691406 ] ] }, { "title": "A. Denoising Diffusion Probabilistic Models", "heading_level": null, "page_id": 4, "polygon": [ [ 48.39808201789856, 389.6693115234375 ], [ 231.1980711221695, 389.6693115234375 ], [ 231.1980711221695, 399.6322937011719 ], [ 48.39808201789856, 399.6322937011719 ] ] }, { "title": "B. Score-Based Generative Models", "heading_level": null, "page_id": 4, "polygon": [ [ 311.18546319007874, 413.8671875 ], [ 454.9419860839844, 413.8671875 ], [ 454.9419860839844, 423.8301696777344 ], [ 311.18546319007874, 424.09621238708496 ] ] }, { "title": "C. Stochastic Differential Equations", "heading_level": null, "page_id": 5, "polygon": [ [ 48.496084839105606, 678.6242752075195 ], [ 196.6032074689865, 678.6242752075195 ], [ 196.6032074689865, 688.587272644043 ], [ 48.496084839105606, 689.0940556526184 ] ] }, { "title": "D. Relation Between DMs", "heading_level": null, "page_id": 5, "polygon": [ [ 310.7765443325043, 646.6473083496094 ], [ 419.67459082603455, 646.6473083496094 ], [ 419.67459082603455, 657.314715385437 ], [ 310.7765443325043, 657.314715385437 ] ] }, { "title": "E. Relation to Other Image SR Generative Models", "heading_level": null, "page_id": 6, "polygon": [ [ 48.152639508247375, 521.3172912597656 ], [ 256.4186096191406, 520.5309906005859 ], [ 256.4186096191406, 531.2802734375 ], [ 48.152639508247375, 531.2802734375 ] ] }, { "title": "IV. IMPROVEMENTS FOR DMS", "heading_level": null, "page_id": 6, "polygon": [ [ 370.9076793193817, 483.69915771484375 ], [ 503.09250569343567, 483.69915771484375 ], [ 503.09250569343567, 493.66217041015625 ], [ 370.9076793193817, 493.66217041015625 ] ] }, { "title": "A. Efficient Sampling", "heading_level": null, "page_id": 6, "polygon": [ [ 310.58514404296875, 581.3302459716797 ], [ 398.69189453125, 581.0536551475525 ], [ 398.69189453125, 591.2932586669922 ], [ 310.58514404296875, 591.5475554466248 ] ] }, { "title": "B. Improved Likelihood", "heading_level": null, "page_id": 7, "polygon": [ [ 310.6435453891754, 99.54425048828125 ], [ 408.1748046875, 99.54425048828125 ], [ 408.1748046875, 109.50726318359375 ], [ 310.6435453891754, 109.50726318359375 ] ] }, { "title": "V. DMS FOR IMAGE SR", "heading_level": null, "page_id": 7, "polygon": [ [ 384.5713691711426, 406.03216552734375 ], [ 488.70294189453125, 404.89311504364014 ], [ 488.70294189453125, 415.99517822265625 ], [ 384.5713691711426, 415.99517822265625 ] ] }, { "title": "A. Concrete Realization of DMs", "heading_level": null, "page_id": 7, "polygon": [ [ 311.6084260940552, 558.6702117919922 ], [ 443.66107177734375, 558.6702117919922 ], [ 443.66107177734375, 568.6332244873047 ], [ 311.6084260940552, 568.6332244873047 ] ] }, { "title": "B. Guidance in Training", "heading_level": null, "page_id": 8, "polygon": [ [ 48.00076773762703, 702.4552993774414 ], [ 149.1668701171875, 702.4552993774414 ], [ 149.1668701171875, 712.4182968139648 ], [ 48.00076773762703, 712.4182968139648 ] ] }, { "title": "C. State Domains", "heading_level": null, "page_id": 8, "polygon": [ [ 310.92701625823975, 594.9784545898438 ], [ 384.51913261413574, 594.9784545898438 ], [ 384.51913261413574, 604.9414672851562 ], [ 310.92701625823975, 605.5793280601501 ] ] }, { "title": "D. Conditioning DMs", "heading_level": null, "page_id": 9, "polygon": [ [ 310.8917784690857, 509.4270324707031 ], [ 401.0888977050781, 509.4270324707031 ], [ 401.0888977050781, 520.0766243934631 ], [ 310.8917784690857, 520.0766243934631 ] ] }, { "title": "E. Corruption Space", "heading_level": null, "page_id": 11, "polygon": [ [ 48.32779794931412, 451.0752868652344 ], [ 133.64451599121094, 451.0752868652344 ], [ 133.64451599121094, 461.03826904296875 ], [ 48.32779794931412, 461.942533493042 ] ] }, { "title": "F. Color Shifting", "heading_level": null, "page_id": 11, "polygon": [ [ 311.97296142578125, 511.326171875 ], [ 380.9368591308594, 511.326171875 ], [ 380.9368591308594, 521.4054508209229 ], [ 310.84957337379456, 521.4054508209229 ] ] }, { "title": "G. Architecture Designs for Denoising", "heading_level": null, "page_id": 12, "polygon": [ [ 47.98686504364014, 107.73357939720154 ], [ 207.07570695877075, 107.73357939720154 ], [ 207.07570695877075, 118.082275390625 ], [ 47.98686504364014, 118.082275390625 ] ] }, { "title": "VI. DIFFUSION-BASED ZERO-SHOT SR", "heading_level": null, "page_id": 12, "polygon": [ [ 90.17398071289062, 529.9551086425781 ], [ 260.00392413139343, 528.6350426673889 ], [ 260.00392413139343, 539.9181060791016 ], [ 90.17398071289062, 539.9196581840515 ] ] }, { "title": "A. Projection-Based", "heading_level": null, "page_id": 12, "polygon": [ [ 47.94274029135704, 714.5822296142578 ], [ 131.50352597236633, 714.5822296142578 ], [ 131.50352597236633, 724.5452270507812 ], [ 47.94274029135704, 724.5452270507812 ] ] }, { "title": "B. Decomposition-Based", "heading_level": null, "page_id": 12, "polygon": [ [ 310.66546869277954, 338.0774230957031 ], [ 413.11901235580444, 336.8895764350891 ], [ 413.11901235580444, 348.0404052734375 ], [ 310.66546869277954, 348.0404052734375 ] ] }, { "title": "C. Posterior Estimation", "heading_level": null, "page_id": 13, "polygon": [ [ 307.8579361438751, 471.01214599609375 ], [ 408.6041259765625, 469.7262396812439 ], [ 408.6041259765625, 480.9751281738281 ], [ 307.8579361438751, 480.9751281738281 ] ] }, { "title": "", "heading_level": null, "page_id": 13, "polygon": [ [ 48.94458693265915, 31.422648042440414 ], [ 55.01643007993698, 31.422648042440414 ], [ 55.01643007993698, 39.20716854929924 ], [ 48.94458693265915, 39.20716854929924 ] ] }, { "title": "VII. DOMAIN-SPECIFIC APPLICATIONS", "heading_level": null, "page_id": 14, "polygon": [ [ 88.36316102743149, 374.03900599479675 ], [ 258.523193359375, 374.03900599479675 ], [ 258.523193359375, 384.2651062011719 ], [ 88.36316102743149, 384.2651062011719 ] ] }, { "title": "A. Medical Imaging", "heading_level": null, "page_id": 14, "polygon": [ [ 48.459716230630875, 487.10516357421875 ], [ 131.1970374584198, 487.10516357421875 ], [ 131.1970374584198, 497.0681457519531 ], [ 48.459716230630875, 497.6573224067688 ] ] }, { "title": "B. Blind Face Restoration", "heading_level": null, "page_id": 14, "polygon": [ [ 311.97406005859375, 140.07623291015625 ], [ 418.61798095703125, 140.00199472904205 ], [ 418.61798095703125, 150.03924560546875 ], [ 311.97406005859375, 150.34214222431183 ] ] }, { "title": "C. AT in Face SR", "heading_level": null, "page_id": 15, "polygon": [ [ 48.54265362024307, 145.18927001953125 ], [ 122.30388218164444, 145.18927001953125 ], [ 122.30388218164444, 155.15228271484375 ], [ 48.54265362024307, 156.33542132377625 ] ] }, { "title": "D. Remote Sensing", "heading_level": null, "page_id": 15, "polygon": [ [ 48.44985803961754, 402.9263000488281 ], [ 127.25965225696564, 402.9263000488281 ], [ 126.98827362060547, 412.8892822265625 ], [ 47.25454553961754, 413.87743377685547 ] ] }, { "title": "VIII. DISCUSSION AND FUTURE WORK", "heading_level": null, "page_id": 15, "polygon": [ [ 352.8550109863281, 95.85711669921875 ], [ 523.4571754932404, 95.208709359169 ], [ 523.4571754932404, 105.82012939453125 ], [ 352.8550109863281, 105.82012939453125 ] ] }, { "title": "A. Color Shifting", "heading_level": null, "page_id": 15, "polygon": [ [ 310.6445667743683, 222.16131591796875 ], [ 382.28094482421875, 222.16131591796875 ], [ 382.28094482421875, 232.12432861328125 ], [ 310.6445667743683, 233.33864450454712 ] ] }, { "title": "B. Computational Costs", "heading_level": null, "page_id": 15, "polygon": [ [ 311.00310945510864, 348.6283264160156 ], [ 409.9581298828125, 348.6283264160156 ], [ 409.9581298828125, 358.59130859375 ], [ 311.00310945510864, 358.59130859375 ] ] }, { "title": "C. Efficient Sampling", "heading_level": null, "page_id": 15, "polygon": [ [ 311.1393549442291, 630.5571594238281 ], [ 399.7615921497345, 630.5571594238281 ], [ 399.7615921497345, 640.5885157585144 ], [ 311.1393549442291, 640.5885157585144 ] ] }, { "title": "D. Corruption Spaces", "heading_level": null, "page_id": 16, "polygon": [ [ 48.17588058114052, 218.8233642578125 ], [ 138.62704467773438, 218.5847246646881 ], [ 138.62704467773438, 228.786376953125 ], [ 48.17588058114052, 229.7779004573822 ] ] }, { "title": "E. Comparability", "heading_level": null, "page_id": 16, "polygon": [ [ 48.89745730161667, 358.8213806152344 ], [ 119.76559406518936, 358.8213806152344 ], [ 119.4980239868164, 368.78436279296875 ], [ 47.70214480161667, 369.86247181892395 ] ] }, { "title": "F. Image Manipulation", "heading_level": null, "page_id": 16, "polygon": [ [ 48.29488563537598, 666.3572158813477 ], [ 143.23296761512756, 666.1338572502136 ], [ 143.23296761512756, 676.3202133178711 ], [ 48.29488563537598, 677.5624537467957 ] ] }, { "title": "G. Cascaded Image Generation", "heading_level": null, "page_id": 16, "polygon": [ [ 310.99771070480347, 239.14837646484375 ], [ 441.8427734375, 239.01838731765747 ], [ 441.8427734375, 249.11138916015625 ], [ 310.99771070480347, 250.21411228179932 ] ] }, { "title": "IX. CONCLUSION", "heading_level": null, "page_id": 16, "polygon": [ [ 397.8849792480469, 444.49212646484375 ], [ 475.8068542480469, 444.49212646484375 ], [ 475.8068542480469, 454.45513916015625 ], [ 397.8849792480469, 455.1179766654968 ] ] }, { "title": "REFERENCES", "heading_level": null, "page_id": 16, "polygon": [ [ 407.60805559158325, 709.4370727539062 ], [ 465.40887451171875, 709.4370727539062 ], [ 465.40887451171875, 719.4000701904297 ], [ 407.60805559158325, 719.4000701904297 ] ] } ], "page_stats": [ { "page_id": 0, "text_extraction_method": "pdftext", "block_counts": [ [ "Span", 266 ], [ "Line", 108 ], [ "Text", 14 ], [ "PageHeader", 2 ], [ "SectionHeader", 2 ] ] }, { "page_id": 1, "text_extraction_method": "pdftext", "block_counts": [ [ "Span", 536 ], [ "Line", 124 ], [ "Text", 11 ], [ "TextInlineMath", 7 ], [ "SectionHeader", 3 ], [ "Equation", 3 ], [ "PageHeader", 2 ] ] }, { "page_id": 2, "text_extraction_method": "pdftext", "block_counts": [ [ "Span", 490 ], [ "Line", 142 ], [ "Text", 8 ], [ "PageHeader", 3 ], [ "Equation", 3 ], [ "TextInlineMath", 2 ], [ "SectionHeader", 1 ] ] }, { "page_id": 3, "text_extraction_method": "pdftext", "block_counts": [ [ "Span", 842 ], [ "Line", 194 ], [ "Text", 10 ], [ "Equation", 5 ], [ "TextInlineMath", 5 ], [ "PageHeader", 3 ], [ "ListItem", 2 ], [ "SectionHeader", 1 ], [ "ListGroup", 1 ] ] }, { "page_id": 4, "text_extraction_method": "pdftext", "block_counts": [ [ "Span", 922 ], [ "Line", 153 ], [ "TextInlineMath", 10 ], [ "Equation", 8 ], [ "Text", 5 ], [ "PageHeader", 2 ], [ "SectionHeader", 2 ], [ "Figure", 1 ], [ "Caption", 1 ], [ "FigureGroup", 1 ] ] }, { "page_id": 5, "text_extraction_method": "pdftext", "block_counts": [ [ "Span", 1313 ], [ "Line", 232 ], [ "TextInlineMath", 10 ], [ "Equation", 9 ], [ "Text", 8 ], [ "PageHeader", 3 ], [ "SectionHeader", 2 ] ] }, { "page_id": 6, "text_extraction_method": "pdftext", "block_counts": [ [ "Span", 372 ], [ "Line", 104 ], [ "Text", 8 ], [ "TextInlineMath", 3 ], [ "SectionHeader", 3 ], [ "PageHeader", 2 ], [ "Equation", 2 ], [ "Figure", 1 ], [ "Caption", 1 ], [ "FigureGroup", 1 ] ] }, { "page_id": 7, "text_extraction_method": "pdftext", "block_counts": [ [ "Span", 302 ], [ "Line", 111 ], [ "Text", 4 ], [ "PageHeader", 3 ], [ "SectionHeader", 3 ], [ "TextInlineMath", 2 ] ] }, { "page_id": 8, "text_extraction_method": "pdftext", "block_counts": [ [ "Span", 771 ], [ "Line", 150 ], [ "TextInlineMath", 9 ], [ "Equation", 5 ], [ "Text", 4 ], [ "PageHeader", 2 ], [ "SectionHeader", 2 ], [ "Figure", 1 ], [ "Caption", 1 ], [ "FigureGroup", 1 ] ] }, { "page_id": 9, "text_extraction_method": "pdftext", "block_counts": [ [ "Span", 287 ], [ "Line", 107 ], [ "Text", 6 ], [ "PageHeader", 3 ], [ "Figure", 1 ], [ "Caption", 1 ], [ "SectionHeader", 1 ], [ "FigureGroup", 1 ] ] }, { "page_id": 10, "text_extraction_method": "pdftext", "block_counts": [ [ "Span", 327 ], [ "Line", 90 ], [ "Text", 4 ], [ "PageHeader", 3 ], [ "Caption", 3 ], [ "Table", 3 ], [ "TableGroup", 2 ], [ "Figure", 1 ], [ "TextInlineMath", 1 ], [ "FigureGroup", 1 ] ] }, { "page_id": 11, "text_extraction_method": "pdftext", "block_counts": [ [ "Span", 367 ], [ "Line", 112 ], [ "Caption", 4 ], [ "PageHeader", 3 ], [ "Text", 3 ], [ "TextInlineMath", 3 ], [ "SectionHeader", 2 ], [ "Table", 1 ], [ "Figure", 1 ], [ "Equation", 1 ], [ "TableGroup", 1 ], [ "FigureGroup", 1 ] ] }, { "page_id": 12, "text_extraction_method": "pdftext", "block_counts": [ [ "Span", 531 ], [ "Line", 122 ], [ "TextInlineMath", 8 ], [ "Text", 6 ], [ "Equation", 6 ], [ "SectionHeader", 4 ], [ "PageHeader", 3 ] ] }, { "page_id": 13, "text_extraction_method": "pdftext", "block_counts": [ [ "Span", 833 ], [ "Line", 149 ], [ "Text", 7 ], [ "TextInlineMath", 6 ], [ "Equation", 4 ], [ "PageHeader", 2 ], [ "Caption", 2 ], [ "SectionHeader", 2 ], [ "Table", 1 ], [ "Figure", 1 ], [ "TableGroup", 1 ], [ "FigureGroup", 1 ] ] }, { "page_id": 14, "text_extraction_method": "pdftext", "block_counts": [ [ "Span", 563 ], [ "Line", 135 ], [ "Text", 7 ], [ "TextInlineMath", 5 ], [ "SectionHeader", 3 ], [ "PageHeader", 2 ], [ "Equation", 2 ] ] }, { "page_id": 15, "text_extraction_method": "pdftext", "block_counts": [ [ "Span", 298 ], [ "Line", 109 ], [ "SectionHeader", 6 ], [ "TextInlineMath", 4 ], [ "Text", 4 ], [ "PageHeader", 3 ] ] }, { "page_id": 16, "text_extraction_method": "pdftext", "block_counts": [ [ "Span", 298 ], [ "Line", 111 ], [ "Text", 8 ], [ "SectionHeader", 6 ], [ "PageHeader", 2 ], [ "ListItem", 1 ] ] }, { "page_id": 17, "text_extraction_method": "pdftext", "block_counts": [ [ "Span", 428 ], [ "Line", 150 ], [ "ListItem", 49 ], [ "PageHeader", 2 ], [ "ListGroup", 2 ], [ "Text", 1 ] ] }, { "page_id": 18, "text_extraction_method": "pdftext", "block_counts": [ [ "Span", 453 ], [ "Line", 153 ], [ "ListItem", 58 ], [ "PageHeader", 2 ], [ "ListGroup", 2 ], [ "Text", 1 ] ] }, { "page_id": 19, "text_extraction_method": "pdftext", "block_counts": [ [ "Span", 438 ], [ "Line", 151 ], [ "ListItem", 51 ], [ "PageHeader", 3 ], [ "Text", 2 ], [ "ListGroup", 2 ] ] }, { "page_id": 20, "text_extraction_method": "pdftext", "block_counts": [ [ "Span", 322 ], [ "Line", 129 ], [ "ListItem", 25 ], [ "Text", 10 ], [ "Picture", 6 ], [ "PageHeader", 3 ], [ "ListGroup", 1 ] ] } ], "debug_data_path": "debug_data\\Moser \u7b49 - 2024 - Diffusion models, image super-resolution, and everything a survey" }