Multi-view image fusion
Autor: | Ricardo Martin-Brualla, Janne Kontkanen, Florian Kainz, Marc Comino Trinidad |
---|---|
Přispěvatelé: | Universitat Politècnica de Catalunya. Doctorat en Computació, Universitat Politècnica de Catalunya. ViRVIG - Grup de Recerca en Visualització, Realitat Virtual i Interacció Gràfica |
Jazyk: | angličtina |
Rok vydání: | 2019 |
Předmět: |
Computer science
Color computer graphics Feature extraction Optical flow ComputingMethodologies_IMAGEPROCESSINGANDCOMPUTERVISION 02 engineering and technology Image color analysis Optical imaging Image (mathematics) Image resolution Machine learning Aprenentatge automàtic 0202 electrical engineering electronic engineering information engineering Monochrome Image fusion Point (geometry) Computer vision Computer architecture Image warping Informàtica::Infografia [Àrees temàtiques de la UPC] business.industry 020207 software engineering Cameras Infografia en color 020201 artificial intelligence & image processing Artificial intelligence business |
Zdroj: | UPCommons. Portal del coneixement obert de la UPC Universitat Politècnica de Catalunya (UPC) ICCV |
Popis: | We present an end-to-end learned system for fusing multiple misaligned photographs of the same scene into a chosen target view. We demonstrate three use cases: 1) color transfer for inferring color for a monochrome view, 2) HDR fusion for merging misaligned bracketed exposures, and 3) detail transfer for reprojecting a high definition image to the point of view of an affordable VR180-camera. While the system can be trained end-to-end, it consists of three distinct steps: feature extraction, image warping and fusion. We present a novel cascaded feature extraction method that enables us to synergetically learn optical flow at different resolution levels. We show that this significantly improves the network’s ability to learn large disparities. Finally, we demonstrate that our alignment architecture outperforms a state-of-the art optical flow network on the image warping task when both systems are trained in an identical manner. |
Databáze: | OpenAIRE |
Externí odkaz: |