A method and apparatus for inverse tone mapping of an LDR image with computer generated imagery components, such components being also called visual effects, are disclosed. The disclosed method includes accessing a first LDR image, the first LDR image being obtained from at least one computer generated imagery component rendered and composited into an LDR reference image or background plate; determining an HDR lighting indication responsive to information extracted from a part of the first LDR image and a respective part of a first intermediate HDR image obtained by applying a first pass inverse tone mapping to the first LDR image; obtaining a second intermediate HDR image by applying a second pass inverse tone mapping to the LDR reference image; obtaining the first HDR image from the computer generated imagery components rendered using HDR lighting indication and composited into the second intermediate HDR image.

One embodiment can provide a machine-vision system. The machine-vision system can include a structured-light projector, a first camera positioned on a first side of the structured-light projector, and a second camera positioned on a second side of the structured-light projector. The first and second cameras are configured to capture images under illumination of the structured-light projector. The structured-light projector can include a laser-based light source.

One embodiment can provide a machine-vision system. The machine-vision system can include a structured-light projector, a first camera positioned on a first side of the structured-light projector, and a second camera positioned on a second side of the structured-light projector. The first and second cameras are configured to capture images under illumination of the structured-light projector. The structured-light projector can include a laser-based light source.

A system and methods for a CODEC driving a real-time light field display for multi-dimensional video streaming, interactive gaming and other light field display applications is provided applying a layered scene decomposition strategy. Multi-dimensional scene data is divided into a plurality of data layers of increasing depths as the distance between a given layer and the plane of the display increases. Data layers are sampled using a plenoptic sampling scheme and rendered using hybrid rendering, such as perspective and oblique rendering, to encode light fields corresponding to each data layer. The resulting compressed, (layered) core representation of the multi-dimensional scene data is produced at predictable rates, reconstructed and merged at the light field display in real-time by applying view synthesis protocols, including edge adaptive interpolation, to reconstruct pixel arrays in stages (e.g. columns then rows) from reference elemental images.

A system and methods for a CODEC driving a real-time light field display for multi-dimensional video streaming, interactive gaming and other light field display applications is provided applying a layered scene decomposition strategy. Multi-dimensional scene data is divided into a plurality of data layers of increasing depths as the distance between a given layer and the plane of the display increases. Data layers are sampled using a plenoptic sampling scheme and rendered using hybrid rendering, such as perspective and oblique rendering, to encode light fields corresponding to each data layer. The resulting compressed, (layered) core representation of the multi-dimensional scene data is produced at predictable rates, reconstructed and merged at the light field display in real-time by applying view synthesis protocols, including edge adaptive interpolation, to reconstruct pixel arrays in stages (e.g. columns then rows) from reference elemental images.

The invention relates to a method (100) for coding a depth lookup table, DLT, (201, 211), the depth lookup table comprising depth value information of at least a part of a 3D picture, the method (100) comprising: selecting (101) a reference depth lookup table (203, 213); determining (103) a difference depth lookup table (205, 215) based on a comparison between depth value information of the depth lookup table to be coded (201, 211) and depth value information of the reference depth lookup table (203, 213); and coding (105) depth value information of the difference depth lookup table (205, 215) according to a predetermined coding rule.

The invention relates to a method (100) for coding a depth lookup table, DLT, (201, 211), the depth lookup table comprising depth value information of at least a part of a 3D picture, the method (100) comprising: selecting (101) a reference depth lookup table (203, 213); determining (103) a difference depth lookup table (205, 215) based on a comparison between depth value information of the depth lookup table to be coded (201, 211) and depth value information of the reference depth lookup table (203, 213); and coding (105) depth value information of the difference depth lookup table (205, 215) according to a predetermined coding rule.

A method, system and computer program product for segmenting generic foreground objects in images and videos. For segmenting generic foreground objects in videos, an appearance stream of an image in a video frame is processed using a first deep neural network. Furthermore, a motion stream of an optical flow image in the video frame is processed using a second deep neural network. The appearance and motion streams are then joined to combine complementary appearance and motion information to perform segmentation of generic objects in the video frame. Generic foreground objects are segmented in images by training a convolutional deep neural network to estimate a likelihood that a pixel in an image belongs to a foreground object. After receiving the image, the likelihood that the pixel in the image is part of the foreground object as opposed to background is then determined using the trained convolutional deep neural network.

An encoding-decoding method and system is provided where the encoding process or system are not a mirror image of the decoding process or system.

An encoding-decoding method and system is provided where the encoding process or system are not a mirror image of the decoding process or system.