[
    {
        "id": "cardoso-thesis",
        "type_id": "phdthesis",
        "tu_id": null,
        "repositum_id": "20.500.12708/209309",
        "title": "Approaching Under-Explored Image-Space Problems with Optimization",
        "date": "2024-12-19",
        "abstract": "This doctoral dissertation delves into three distinct yet interconnected problems in the realm of interactive image-space computing in computer graphics, each of which has not been tackled by existing literature.The first problem centers on the prediction of visual error metrics in real-time applications, specifically in the context of content-adaptive shading and shading reuse. Utilizing convolutional neural networks, this research aims to estimate visual errors without requiring reference or rendered images. The models developed can account for 70%–90% of the variance and achieve computation times that are an order of magnitude faster than existing methods. This enables a balance between resource-saving and visual quality, particularly in deferred shading pipelines, and can achieve up to twice the performance compared to state-of-the-art methods depending on the portion of unseen image regions. The second problem focuses on the burgeoning field of light-field cameras and the challenges associated with depth prediction. This research argues for the refinement of cost volumes rather than depth maps to increase the accuracy of depth predictions. A set of cost-volume refinement algorithms is proposed, which dynamically operate at runtime to find optimal solutions, thereby enhancing the accuracy and reliability of depth estimation in light fields.The third problem tackles the labor-intensive nature of hand-drawn animation, specifically in the detailing of character eyes. An unsupervised network is introduced that blends inpainting and image-to-image translation techniques. This network employs a novel style-aware clustering method and a dual-discriminator optimization strategy with a triple-reconstruction loss. The result is an improvement in the level of detail and artistic consistency in hand-drawn animation, preferred over existing work 95.16% of the time according to a user study.Optimization techniques are the common thread that ties these problems together. While dynamic optimization at runtime is employed for cost volume refinement, deep-learning methods are used offline to train global solutions for the other two problems. This research not only fills gaps in the existing literature but also paves the way for future explorations in the field of computer graphics and optimization, offering new avenues for both academic research and practical applications.",
        "authors_et_al": false,
        "substitute": null,
        "main_image": null,
        "sync_repositum_override": "date",
        "repositum_presentation_id": null,
        "authors": [
            1639
        ],
        "ac_number": "AC17414787",
        "date_end": "2024-12-19",
        "date_start": "2019-04",
        "doi": "10.34726/hss.2025.128664",
        "matrikelnr": "11937133",
        "open_access": "yes",
        "pages": "110",
        "reviewer_1": [
            1825
        ],
        "reviewer_2": [
            5420
        ],
        "rigorosum": "2024-12-19",
        "supervisor": [
            193
        ],
        "research_areas": [
            "Perception",
            "Rendering"
        ],
        "keywords": [
            "variable-rate shading",
            "light-fields",
            "limited animation",
            "anime",
            "convolutional neural networks"
        ],
        "weblinks": [],
        "files": [
            {
                "description": null,
                "filetitle": "thesis",
                "main_file": true,
                "use_in_gallery": false,
                "access": "public",
                "name": "cardoso-thesis-thesis.pdf",
                "type": "application/pdf",
                "size": 47447576,
                "path": "Publication:cardoso-thesis",
                "url": "https://www.cg.tuwien.ac.at/research/publications/2024/cardoso-thesis/cardoso-thesis-thesis.pdf",
                "thumb_image_sizes": [
                    16,
                    64,
                    100,
                    175,
                    300,
                    600
                ],
                "thumb_url": "https://www.cg.tuwien.ac.at/research/publications/2024/cardoso-thesis/cardoso-thesis-thesis:thumb{{size}}.png"
            }
        ],
        "projects_workgroups": [
            "EVOCATION"
        ],
        "url": "https://www.cg.tuwien.ac.at/research/publications/2024/cardoso-thesis/",
        "__class": "Publication"
    },
    {
        "id": "cardoso-2024-r-c",
        "type_id": "inproceedings",
        "tu_id": null,
        "repositum_id": "20.500.12708/209907",
        "title": "Re:Draw - Context Aware Translation as a Controllable Method for Artistic Production",
        "date": "2024-08",
        "abstract": "We introduce context-aware translation, a novel method that combines the benefits of inpainting and image-to-image translation, respecting simultaneously the original input and contextual relevance – where existing methods fall short. By doing so, our method opens new avenues for the controllable use of AI within artistic creation, from animation to digital art.\nAs an use case, we apply our method to redraw any hand-drawn animated character eyes based on any design specifications – eyes serve as a focal point that captures viewer attention and conveys a range of emotions; however, the labor-intensive na-\nture of traditional animation often leads to compromises in the complexity and consistency of eye design. Furthermore, we remove the need for production data for training and introduce a new character recognition method that surpasses existing work\nby not requiring fine-tuning to specific productions.\nThis proposed use case could help maintain consistency throughout production and unlock bolder and\nmore detailed design choices without the production cost drawbacks. A user study shows contextaware translation is preferred over existing work 95.16% of the time.",
        "authors_et_al": false,
        "substitute": null,
        "main_image": {
            "description": null,
            "filetitle": "image",
            "main_file": false,
            "use_in_gallery": true,
            "access": "public",
            "image_width": 343,
            "image_height": 294,
            "name": "cardoso-2024-r-c-image.bmp",
            "type": "image/bmp",
            "size": 303462,
            "path": "Publication:cardoso-2024-r-c",
            "url": "https://www.cg.tuwien.ac.at/research/publications/2024/cardoso-2024-r-c/cardoso-2024-r-c-image.bmp",
            "thumb_image_sizes": [
                16,
                64,
                100,
                175,
                300,
                600
            ],
            "thumb_url": "https://www.cg.tuwien.ac.at/research/publications/2024/cardoso-2024-r-c/cardoso-2024-r-c-image:thumb{{size}}.png"
        },
        "sync_repositum_override": "date,projects",
        "repositum_presentation_id": null,
        "authors": [
            1639,
            5437,
            1519,
            193
        ],
        "booktitle": "Proceedings of the Thirty-Third International Joint Conference on Artificial Intelligence (IJCAI-24)",
        "date_from": "2024-08-03",
        "date_to": "2024-08-09",
        "doi": "10.24963/ijcai.2024/842",
        "event": "33rd International Joint Conference on Artificial Intelligence (IJCAI 2024)",
        "isbn": "978-1-956792-04-1",
        "lecturer": [
            1639
        ],
        "location": "Jeju Island",
        "pages": "9",
        "pages_from": "7609",
        "pages_to": "7617",
        "publisher": "International Joint Conferences on Artificial Intelligence",
        "research_areas": [
            "Rendering"
        ],
        "keywords": [
            "Application domains: Images, movies and visual arts",
            "Application domains: Computer Graphics and Animation",
            "Methods and resources: AI systems for collaboration and co-creation",
            "Methods and resources: Machine learning, deep learning, neural models, reinforcement learning",
            "Theory and philosophy of arts and creativity in AI systems: Social (multi-agent) creativity and human-computer co-creation"
        ],
        "weblinks": [],
        "files": [
            {
                "description": null,
                "filetitle": "image",
                "main_file": false,
                "use_in_gallery": true,
                "access": "public",
                "image_width": 343,
                "image_height": 294,
                "name": "cardoso-2024-r-c-image.bmp",
                "type": "image/bmp",
                "size": 303462,
                "path": "Publication:cardoso-2024-r-c",
                "url": "https://www.cg.tuwien.ac.at/research/publications/2024/cardoso-2024-r-c/cardoso-2024-r-c-image.bmp",
                "thumb_image_sizes": [
                    16,
                    64,
                    100,
                    175,
                    300,
                    600
                ],
                "thumb_url": "https://www.cg.tuwien.ac.at/research/publications/2024/cardoso-2024-r-c/cardoso-2024-r-c-image:thumb{{size}}.png"
            },
            {
                "description": null,
                "filetitle": "paper",
                "main_file": true,
                "use_in_gallery": false,
                "access": "public",
                "name": "cardoso-2024-r-c-paper.pdf",
                "type": "application/pdf",
                "size": 2952059,
                "path": "Publication:cardoso-2024-r-c",
                "url": "https://www.cg.tuwien.ac.at/research/publications/2024/cardoso-2024-r-c/cardoso-2024-r-c-paper.pdf",
                "thumb_image_sizes": [
                    16,
                    64,
                    100,
                    175,
                    300,
                    600
                ],
                "thumb_url": "https://www.cg.tuwien.ac.at/research/publications/2024/cardoso-2024-r-c/cardoso-2024-r-c-paper:thumb{{size}}.png"
            }
        ],
        "projects_workgroups": [
            "EVOCATION"
        ],
        "url": "https://www.cg.tuwien.ac.at/research/publications/2024/cardoso-2024-r-c/",
        "__class": "Publication"
    },
    {
        "id": "cardoso-2022-rtpercept",
        "type_id": "journalpaper",
        "tu_id": null,
        "repositum_id": "20.500.12708/142206",
        "title": "Training and Predicting Visual Error for Real-Time Applications",
        "date": "2022-05",
        "abstract": "Visual error metrics play a fundamental role in the quantification of perceived image similarity. Most recently, use cases for them in real-time applications have emerged, such as content-adaptive shading and shading reuse to increase performance and improve efficiency. A wide range of different metrics has been established, with the most sophisticated being capable of capturing the perceptual characteristics of the human visual system. However, their complexity, computational expense, and reliance on reference images to compare against prevent their generalized use in real-time, restricting such applications to using only the simplest available metrics.\n\nIn this work, we explore the abilities of convolutional neural networks to predict a variety of visual metrics without requiring either reference or rendered images. Specifically, we train and deploy a neural network to estimate the visual error resulting from reusing shading or using reduced shading rates. The resulting models account for 70%--90% of the variance while achieving up to an order of magnitude faster computation times. Our solution combines image-space information that is readily available in most state-of-the-art deferred shading pipelines with reprojection from previous frames to enable an adequate estimate of visual errors, even in previously unseen regions. We describe a suitable convolutional network architecture and considerations for data preparation for training. We demonstrate the capability of our network to predict complex error metrics at interactive rates in a real-time application that implements content-adaptive shading in a deferred pipeline. Depending on the portion of unseen image regions, our approach can achieve up to 2x performance compared to state-of-the-art methods.",
        "authors_et_al": false,
        "substitute": null,
        "main_image": {
            "description": null,
            "filetitle": "teaser",
            "main_file": false,
            "use_in_gallery": true,
            "access": "public",
            "image_width": 1920,
            "image_height": 1088,
            "name": "cardoso-2022-rtpercept-teaser.png",
            "type": "image/png",
            "size": 2493649,
            "path": "Publication:cardoso-2022-rtpercept",
            "url": "https://www.cg.tuwien.ac.at/research/publications/2022/cardoso-2022-rtpercept/cardoso-2022-rtpercept-teaser.png",
            "thumb_image_sizes": [
                16,
                64,
                100,
                175,
                300,
                600
            ],
            "thumb_url": "https://www.cg.tuwien.ac.at/research/publications/2022/cardoso-2022-rtpercept/cardoso-2022-rtpercept-teaser:thumb{{size}}.png"
        },
        "sync_repositum_override": null,
        "repositum_presentation_id": null,
        "authors": [
            1639,
            1650,
            868,
            1921,
            193
        ],
        "cfp": {
            "name": "cfp.pdf",
            "type": "application/pdf",
            "error": "0",
            "size": "1227280",
            "orig_name": "cfp.pdf",
            "ext": "pdf"
        },
        "date_from": "2022-05-03",
        "date_to": "2022-05-05",
        "doi": "10.1145/3522625",
        "event": "ACM SIGGRAPH Symposium on Interactive 3D Graphics and Games",
        "issn": "2577-6193",
        "journal": "Proceedings of the ACM on Computer Graphics and Interactive Techniques",
        "lecturer": [
            1639
        ],
        "location": "online",
        "number": "1",
        "open_access": "yes",
        "pages": "17",
        "pages_from": "1",
        "pages_to": "17",
        "publisher": "Association for Computing Machinery",
        "volume": "5",
        "research_areas": [
            "Perception",
            "Rendering"
        ],
        "keywords": [
            "perceptual error",
            "variable rate shading",
            "real-time"
        ],
        "weblinks": [
            {
                "href": "https://jaliborc.github.io/rt-percept/",
                "caption": "Paper Website",
                "description": null,
                "main_file": 1
            }
        ],
        "files": [
            {
                "description": null,
                "filetitle": "paper",
                "main_file": true,
                "use_in_gallery": false,
                "access": "public",
                "name": "cardoso-2022-rtpercept-paper.pdf",
                "type": "application/pdf",
                "size": 54709850,
                "path": "Publication:cardoso-2022-rtpercept",
                "url": "https://www.cg.tuwien.ac.at/research/publications/2022/cardoso-2022-rtpercept/cardoso-2022-rtpercept-paper.pdf",
                "thumb_image_sizes": [
                    16,
                    64,
                    100,
                    175,
                    300,
                    600
                ],
                "thumb_url": "https://www.cg.tuwien.ac.at/research/publications/2022/cardoso-2022-rtpercept/cardoso-2022-rtpercept-paper:thumb{{size}}.png"
            },
            {
                "description": null,
                "filetitle": "teaser",
                "main_file": false,
                "use_in_gallery": true,
                "access": "public",
                "image_width": 1920,
                "image_height": 1088,
                "name": "cardoso-2022-rtpercept-teaser.png",
                "type": "image/png",
                "size": 2493649,
                "path": "Publication:cardoso-2022-rtpercept",
                "url": "https://www.cg.tuwien.ac.at/research/publications/2022/cardoso-2022-rtpercept/cardoso-2022-rtpercept-teaser.png",
                "thumb_image_sizes": [
                    16,
                    64,
                    100,
                    175,
                    300,
                    600
                ],
                "thumb_url": "https://www.cg.tuwien.ac.at/research/publications/2022/cardoso-2022-rtpercept/cardoso-2022-rtpercept-teaser:thumb{{size}}.png"
            }
        ],
        "projects_workgroups": [
            "EVOCATION"
        ],
        "url": "https://www.cg.tuwien.ac.at/research/publications/2022/cardoso-2022-rtpercept/",
        "__class": "Publication"
    },
    {
        "id": "cardoso-2021-cost",
        "type_id": "inproceedings",
        "tu_id": 301688,
        "repositum_id": null,
        "title": "Cost Volume Refinement for Depth Prediction",
        "date": "2021-01-10",
        "abstract": "Light-field cameras are becoming more popular in\nthe consumer market. Their data redundancy allows, in theory,\nto accurately refocus images after acquisition and to predict the\ndepth of each point visible from the camera. Combined, these\ntwo features allow for the generation of full-focus images, which\nis impossible in traditional cameras.\nMultiple methods for depth prediction from light fields (or\nstereo) have been proposed over the years. A large subset of\nthese methods relies on cost-volume estimates – 3D objects where\neach layer represents a heuristic of whether each point in the\nimage is at a certain distance from the camera. Generally, this\nvolume is used to regress a depth map, which is then refined\nfor better results. In this paper, we argue that refining the cost\nvolumes is superior to refining the depth maps in order to further\nincrease the accuracy of depth predictions. We propose a set of\ncost-volume refinement algorithms and show their effectiveness.",
        "authors_et_al": false,
        "substitute": null,
        "main_image": {
            "description": null,
            "filetitle": "header",
            "main_file": false,
            "use_in_gallery": false,
            "access": "public",
            "image_width": 217,
            "image_height": 145,
            "name": "cardoso-2021-cost-header.jpg",
            "type": "image/jpeg",
            "size": 34129,
            "path": "Publication:cardoso-2021-cost",
            "url": "https://www.cg.tuwien.ac.at/research/publications/2021/cardoso-2021-cost/cardoso-2021-cost-header.jpg",
            "thumb_image_sizes": [
                16,
                64,
                100,
                175,
                300,
                600
            ],
            "thumb_url": "https://www.cg.tuwien.ac.at/research/publications/2021/cardoso-2021-cost/cardoso-2021-cost-header:thumb{{size}}.png"
        },
        "sync_repositum_override": null,
        "repositum_presentation_id": null,
        "authors": [
            1639,
            1801,
            193
        ],
        "booktitle": "Proceedings of the 25th International Conference on Pattern Recognition",
        "cfp": {
            "name": "1.html",
            "type": "text/html",
            "error": "0",
            "size": "51497",
            "orig_name": "1.html",
            "ext": "html"
        },
        "date_from": "2021-01-10",
        "date_to": "2021-01-15",
        "doi": "10.1109/ICPR48806.2021.9412730",
        "event": "25th International Conference on Pattern Recognition (ICPR)",
        "isbn": "978-1-7281-8809-6",
        "lecturer": [
            1639
        ],
        "location": "Milan, Italy",
        "open_access": "yes",
        "pages_from": "354",
        "pages_to": "361",
        "publisher": "IEEE",
        "research_areas": [
            "Rendering"
        ],
        "keywords": [
            "depth reconstruction",
            "light fields",
            "cost volumes"
        ],
        "weblinks": [],
        "files": [
            {
                "description": "Acknowledgements section added.",
                "filetitle": "amended-paper",
                "main_file": true,
                "use_in_gallery": false,
                "access": "public",
                "name": "cardoso-2021-cost-amended-paper.pdf",
                "type": "application/pdf",
                "size": 11789393,
                "path": "Publication:cardoso-2021-cost",
                "url": "https://www.cg.tuwien.ac.at/research/publications/2021/cardoso-2021-cost/cardoso-2021-cost-amended-paper.pdf",
                "thumb_image_sizes": [
                    16,
                    64,
                    100,
                    175,
                    300,
                    600
                ],
                "thumb_url": "https://www.cg.tuwien.ac.at/research/publications/2021/cardoso-2021-cost/cardoso-2021-cost-amended-paper:thumb{{size}}.png"
            },
            {
                "description": null,
                "filetitle": "header",
                "main_file": false,
                "use_in_gallery": false,
                "access": "public",
                "image_width": 217,
                "image_height": 145,
                "name": "cardoso-2021-cost-header.jpg",
                "type": "image/jpeg",
                "size": 34129,
                "path": "Publication:cardoso-2021-cost",
                "url": "https://www.cg.tuwien.ac.at/research/publications/2021/cardoso-2021-cost/cardoso-2021-cost-header.jpg",
                "thumb_image_sizes": [
                    16,
                    64,
                    100,
                    175,
                    300,
                    600
                ],
                "thumb_url": "https://www.cg.tuwien.ac.at/research/publications/2021/cardoso-2021-cost/cardoso-2021-cost-header:thumb{{size}}.png"
            },
            {
                "description": null,
                "filetitle": "original-paper",
                "main_file": false,
                "use_in_gallery": false,
                "access": "public",
                "name": "cardoso-2021-cost-original-paper.pdf",
                "type": "application/pdf",
                "size": 11772629,
                "path": "Publication:cardoso-2021-cost",
                "url": "https://www.cg.tuwien.ac.at/research/publications/2021/cardoso-2021-cost/cardoso-2021-cost-original-paper.pdf",
                "thumb_image_sizes": [
                    16,
                    64,
                    100,
                    175,
                    300,
                    600
                ],
                "thumb_url": "https://www.cg.tuwien.ac.at/research/publications/2021/cardoso-2021-cost/cardoso-2021-cost-original-paper:thumb{{size}}.png"
            }
        ],
        "projects_workgroups": [
            "EVOCATION"
        ],
        "url": "https://www.cg.tuwien.ac.at/research/publications/2021/cardoso-2021-cost/",
        "__class": "Publication"
    }
]