Interactive HDR Image-Based Rendering from Unstructured LDR Photographs
| Autor: | Loubna Lechlek, Romuald Perrot, Mohamed Chaouki Babahenini, Daniel Meneveaux, Mickaël Ribardière |
|---|---|
| Přispěvatelé: | Université Mohamed Khider de Biskra (BISKRA), Université de Poitiers - Faculté de Sciences fondamentales et appliquées, Université de Poitiers, Synthèse et analyse d'images (XLIM-ASALI), XLIM (XLIM), Université de Limoges (UNILIM)-Centre National de la Recherche Scientifique (CNRS)-Université de Limoges (UNILIM)-Centre National de la Recherche Scientifique (CNRS) |
| Jazyk: | angličtina |
| Rok vydání: | 2019 |
| Předmět: |
Pixel
Point (typography) Computer science General Engineering Point cloud Process (computing) ComputingMethodologies_IMAGEPROCESSINGANDCOMPUTERVISION interactive rendering 020207 software engineering 02 engineering and technology Image-based modeling and rendering Computer Graphics and Computer-Aided Design [INFO.INFO-GR]Computer Science [cs]/Graphics [cs.GR] Image (mathematics) Human-Computer Interaction high-dynamic range images Depth map Computer graphics (images) 0202 electrical engineering electronic engineering information engineering 020201 artificial intelligence & image processing Point-based proxy High dynamic range Image-based rendering ComputingMethodologies_COMPUTERGRAPHICS |
| Zdroj: | Computers and Graphics Computers and Graphics, Elsevier, 2019, 84, ⟨10.1016/j.cag.2019.07.010⟩ |
| ISSN: | 0097-8493 |
| DOI: | 10.1016/j.cag.2019.07.010⟩ |
| Popis: | International audience; This paper proposes an interactive High Dynamic Range (HDR) image-based rendering system, dedicated to manually acquired photographs. It only relies on a point-based geometric proxy and the original photographs, calibrated using a standard structure-from-motion process. First, a depth map is estimated for each new rendered viewpoint, based on the point cloud. Second, pixel values are reconstructed from the original photographs, using a blending model that also handles occlusion. Our system can be used for producing HDR images from several series of unaligned photographs with different exposures. As shown in the results, it proves efficient with various types of objects, implemented in WebGL, making it practical for many purposes. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|
Full Text from ScienceDirect