Zobrazeno 1 - 10
of 58
pro vyhledávání: '"Pedro V. Sander"'
Publikováno v:
IEEE Transactions on Visualization and Computer Graphics. 28:4274-4288
We introduce the problem of clustering the set of vertices in a given 3D mesh. The problem is motivated by the need for value engineering in architectural projects. We first derive a max-norm based metric to estimate the geometric disparity between a
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::bc088f6c0f1d5c1aa2c6fff0773f8a84
https://doi.org/10.1109/tvcg.2021.3085685
https://doi.org/10.1109/tvcg.2021.3085685
We propose an approach to simulate and render realistic water animation from a single still input photograph. We first segment the water surface, estimate rendering parameters, and compute water reflection textures with a combination of neural networ
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::40452b05e30aca79f7d88310cc3ebfa8
http://arxiv.org/abs/2210.02553
http://arxiv.org/abs/2210.02553
Implicit radiance functions emerged as a powerful scene representation for reconstructing and rendering photo-realistic views of a 3D scene. These representations, however, suffer from poor editability. On the other hand, explicit representations suc
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::e934712708680bebeafa9c6eb56de9b1
Publikováno v:
2021 IEEE/CVF International Conference on Computer Vision (ICCV).
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::886f30b5000fa06ef5798c6283bb7e04
https://doi.org/10.1109/iccv48922.2021.00202
https://doi.org/10.1109/iccv48922.2021.00202
Publikováno v:
ACM Transactions on Graphics. 38:1-11
We propose a novel learning method to rectify document images with various distortion types from a single input image. As opposed to previous learning-based methods, our approach seeks to first learn the distortion flow on input image patches rather
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::e4abed534d7e202e2b92161b7fe81782
https://doi.org/10.1145/3355089.3356563
https://doi.org/10.1145/3355089.3356563
Publikováno v:
ACM Transactions on Graphics. 38:1-18
We propose a new algorithm for color transfer between images that have perceptually similar semantic structures. We aim to achieve a more accurate color transfer that leverages semantically-meaningful dense correspondence between images. To accomplis
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::75178b27b72e9d28a526ccdc0c26fbf8
https://doi.org/10.1145/3292482
https://doi.org/10.1145/3292482
Publikováno v:
IEEE transactions on visualization and computer graphics. 28(8)
We propose a novel framework to produce cartoon videos by fetching the color information from two input keyframes while following the animated motion guided by a user sketch. The key idea of the proposed approach is to estimate the dense cross-domain
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::d0a9bcf41b0bdb15bb1731fbed93ac65
https://pubmed.ncbi.nlm.nih.gov/33400651
https://pubmed.ncbi.nlm.nih.gov/33400651
Neural Radiance Field (NeRF) has gained considerable attention recently for 3D scene reconstruction and novel view synthesis due to its remarkable synthesis quality. However, image blurriness caused by defocus or motion, which often occurs when captu
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::f513e6d1d6ae2172bc2a56ced47ddb9a
In this paper, we propose an image compression algorithm called Microshift. We employ an algorithm hardware co-design methodology, yielding a hardware-friendly compression approach with low power consumption. In our method, the image is first micro-s
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::d9693fc6cfdc8d53a9310aaa0aec1831
Publikováno v:
Computer-Aided Design. 142:103120
Various techniques have been proposed to improve the level of automation in stages of architectural design. We present an interactive interface, along with optimization algorithms focused on designing early stage symbolic architecture. The architect
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::7904916e27b3ca90ee5ebc9dc5127519
https://doi.org/10.1016/j.cad.2021.103120
https://doi.org/10.1016/j.cad.2021.103120