Nvidia Corporation

Morpho Detection, Inc.

Seungseok Oh

Samit Kumar Basu

Sean Midthun Pieper

Pedro Andres Garzon

Systems and techniques for noise reduction in video are described. Example implementations provide improved motion-adaptive temporal or spatio-temporal noise reduction that use an improved blending of the current frame with previous frames. The improved blending may be particularly effective for processing video captured in noisy environments such as low-light and/or mobile environments. In some example implementations, the improved blending is based on more accurately distinguishing between pixel difference in adjacent images that are caused by motion rather than noise.

Techniques for reducing noise in video

A helical CT scanner for imaging an object is provided. The helical CT scanner includes an X-ray emitter configured to emit X-ray beams towards the object, and a detector array positioned opposite the X-ray emitter, the detector array including a plurality of discrete detector blocks arranged in a two-dimensional grid, each detector block including a plurality of pixels, wherein at least one first gap is defined between adjacent detector blocks in a first direction, and wherein at least one second gap is defined between adjacent detector blocks in a second direction. The helical CT scanner further includes a processing device communicatively coupled to said detector array, said processing device configured to reconstruct an image of the object based on image data acquired using said detector array.

Growing community of inventors

Fremont, CA, United States of America

Seungseok Oh