Abstract We present a fast reconstruction filtering method for images generated with Monte Carlo–based rendering techniques. Our approach specializes in reducing global illumination noise in the presence of depth‐of‐field effects at very low sampling rates and interactive frame rates. We employ edge‐aware filtering in the sample space to locally improve outgoing radiance of each sample. The improved samples are then distributed in the image plane using a fast, linear manifold‐based approach supporting very large circles of confusion. We evaluate our filter by applying it to several images containing noise caused by Monte Carlo–simulated global illumination, area light sources and depth of field. We show that our filter can efficiently denoise such images at interactive frame rates on current GPUs and with as few as 4–16 samples per pixel. Our method operates only on the colour and geometric sample information output of the initial rendering process. It does not make any assumptions on the underlying rendering technique and sampling strategy and can therefore be implemented completely as a post‐process filter.

A dynamic procedure for selective information fusion from multiple image frames is derived from robust error estimation theory. The fusion rate is driven by the anisotropic gain function, defined to be the difference between the Gaussian smoothed-edge maps of a given input frame and of an evolving synthetic output frame. The gain function achieves both selection and rapid fusion of relatively sharper features from each input frame compared to the synthetic frame. Effective applications are demonstrated for image sharpening in imaging through atmospheric turbulence, for multispectral fusion of the RGB spectral components of a scene, for removal of blurred visual obstructions from in front of a distant focused scene, and for high-resolution two-dimensional display of three-dimensional objects in microscopy.