微軟研究去手振修圖功能 @ 謝昌勳

微軟研究去手振修圖功能
http://chinese.engadget.com/2010/08/03/microsoft-algorithm-uses-six-axis-motion-sensors-to-fix-blurry-s/

去手振修圖軟體演算法，來配合加速感應器、陀螺儀使用，將拍攝的影像修回正軌。

這套軟體演算法，是以一些三度空間慣性測量感應器套件為基礎，並透過加速感應器、陀螺儀來紀錄拍攝過程中，使用者手部位移的資訊，最後則是削減掉照片受到手振的影響，讓模糊的影像重新聚焦；不過目前這套演算法也不算完美，本體的影像恢復正常之餘，背景可能反而會出現一些奇怪的線條，但整體來看，已經算是相當有進展了。

至於這東西有沒有可能被用在單眼、隨身相機、手機等產品上面，目前並不清楚就是；跳轉後有使用前使用後的 GIF 小圖，更多高解析的對照圖，

微專利：支援六軸感應的遙控器

http://chinese.engadget.com/2010/07/06/microsoft-patent-application-proposes-six-axis-remote-thats-but/

ref:

http://research.microsoft.com/en-us/um/redmond/groups/ivm/imudeblurring/

Image Deblurring using Inertial Measurement Sensors

SIGGRAPH 2010

Neel Joshi	Sing Bing Kang	C. Lawrence Zitnick	Richard Szeliski
Microsoft Research

An SLR Camera instrumented with our image deblurring attachment that uses inertial measurement sensors and the input image in an “aided blind-deconvolution” algorithm to automatically deblur images with spatially-varying blurs (first two images). A blurry input image (third image) and the result of our method (fourth image).

Abstract

We present a deblurring algorithm that uses a hardware attachment coupled with a natural image prior to deblur images from consumer cameras. Our approach uses a combination of inexpensive gyroscopes and accelerometers in an energy optimization framework to estimate a blur function from the camera’s acceleration and angular velocity during an exposure. We solve for the camera motion at a high sampling rate during an exposure and infer the latent image using a joint optimization. Our method is completely automatic, handles per-pixel, spatially-varying blur, and out-performs the current leading image-based methods. Our experiments show that it handles large kernels – up to at least 100 pixels, with a typical size of 30 pixels. We also present a method to perform “ground-truth” measurements of camera motion blur. We use this method to validate our hardware and deconvolution approach. To the best of our knowledge, this is the first work that uses 6 DOF inertial sensors for dense, per-pixel spatially-varying image deblurring and the first work to gather dense ground-truth measurements for camera-shake blur.

Examples