Camera Depth of Field Manipulation for Pre- and Post-Image Capture | AISC

Channel:
Canada LLMs Explained - Aggregate Intellect - AI.SCIENCE
Subscribers:
22,300
Published on ● Video Link: https://www.youtube.com/watch?v=XO2Nt60pvmU


Duration: 49:50
117 views
3

For slides and more information on the paper, visit https://ai.science/e/camera-depth-of-field-manipulation-for-pre-and-post-image-capture--j2UE14MxghMc6wNRXNpH

Speaker: Abdullah Abuolaim; Host: Mahdi Biparva

Motivation:
Defocus blur arises in images that are captured with a shallow depth of field due to the use of a wide aperture. Correcting defocus blur is challenging because the blur is spatially varying and difficult to estimate. We review an effective defocus deblurring method that exploits data available on dual-pixel (DP) sensors found on most modern cameras. DP sensors are used to assist a camera’s auto-focus by capturing two sub-aperture views of the scene in a single image shot. The two sub-aperture images are used to calculate the appropriate lens position to focus on a particular scene region and are discarded afterwards. We introduce a deep neural network (DNN) architecture that uses these discarded sub-aperture images to reduce defocus blur. A key contribution of our effort is a carefully captured dataset of 500 scenes (2000 images) where each scene has: (i) an image with defocus blur captured at a large aperture; (ii) the two associated DP sub-aperture views; and (iii) the corresponding all-in-focus image captured with a small aperture. Our proposed DNN produces results that are significantly better than conventional single image methods in terms of both quantitative and perceptual metrics – all from data that is already available on the camera but ignored.

------
#AISC hosts 3-5 live sessions like this on various AI research, engineering, and product topics every week! Visit https://ai.science for more details



Other Videos By LLMs Explained - Aggregate Intellect - AI.SCIENCE


2020-10-15Designing quantum computers with generative models | AISC
2020-10-15Explainable AI for Time Series - Literature Review | AISC
2020-10-15Towards a Critical Race Methodology in Algorithmic Fairness | AISC
2020-10-14An eye on AI in Healthcare | AISC
2020-10-13Some Salient Issues with Saliency Models | AISC
2020-10-13The Messy Side of AI Products | AISC
2020-10-09Human Aware AI: Reducing Transportation Energy of a City by Influencing Individual Behaviour
2020-10-08Policy Priority Inference: Simulations for Government Strategy | AISC
2020-10-07Inferring the 3D Standing Spine Posture from 2D Radiographs | AISC
2020-10-06Knowledge Extraction from Multimodal & Multilingual sources | AISC
2020-10-01Camera Depth of Field Manipulation for Pre- and Post-Image Capture | AISC
2020-09-30[MOREL] Unsupervised Video Object Segmentation for Deep Reinforcement Learning
2020-09-29Dealing with Bias and Fairness in Data Science Systems: A Practical Hands-on Tutorial | AISC
2020-09-29Overview: Machine Learning for Quantum Matter Research | AISC
2020-09-25Overview of Machine Learning for Knowledge Graphs | AISC
2020-09-24Integrating Physics into Machine Learning Models for Scientific Discovery | AISC
2020-09-24Applications of Blockchain to IoT Security | AISC
2020-09-24Human-Technology Systems for Intelligent Civil Infrastructure Operation and Maintenance | AISC
2020-09-23The AI Design Sprint -- setting your AI Initiative up for delivery success! | AISC
2020-09-23explainX - Explainable AI for model developers | AISC
2020-09-22Statistical Issues in Agent-Based Models | AISC