Method and device for processing multi-view video data
A method and a device for processing multi-view video data. The multi-view video data includes at least one part of a decoded image of at least one view of the multi-view video, from an encoded data stream representative of the multi-view video. At least one item of data, referred to as synthesis data, is obtained from at least the one part of the decoded image, and at least one image of an intermediate view of the multi-view video not encoded in the encoded data stream is synthesized from at least the one part of the decoded image and from the synthesis data obtained.
1. A method for processing multi-view video data, the processing method being implemented by processing device and comprising:
obtaining at least one part of a decoded texture image of at least one view of the multi-view video, from a decoding device that has received and decoded an encoded data stream representative of the multi-view video, the encoded data stream containing no depth map data:
extracting at least one part of a depth map from at least said one part of the decoded texture image, referred to as synthesis data, and
synthesizing at least one image of an intermediate view of the multi-view video not encoded in said encoded data stream, from at least said one part of the decoded texture image and from said synthesis data obtained.
2. The data processing method according to claim 1 , comprising decoding from the encoded data stream at least one item of data that enables modification of the synthesis data obtained or to control the obtaining of the synthesis data.
3. The method for processing multi-view video data according to claim 1 , wherein the synthesis data is obtained using a neural network.
4. The method for processing multi-view video data according to claim 2 , wherein the at least one item of data decoded from the encoded data stream comprises refinement data of said synthesis data, and the method further comprises modifying said synthesis data from said decoded refinement data.
5. The method for processing multi-view video data according to claim 4 , wherein the synthesis data is modified by adding the refinement data to the synthesis data.
6. The method for processing multi-view video data according to claim 2 , wherein the at least one item of data decoded from the encoded data stream comprises a control parameter, the method further comprising applying said control parameter when obtaining said synthesis data.
7. The method for processing multi-view video data according to claim 1 , wherein obtaining the synthesis data comprises:
modifying said synthesis data obtained using a neural network.
8. The method for processing multi-view video data according to claim 7 , wherein the at least one item of data decoded from the encoded data stream comprises a control parameter, which corresponds to an update parameter of said neural network used to modify said synthesis data, the method further comprising applying said control parameter when obtaining said synthesis data.
9. The method for processing multi-view video data according to claim 1 , wherein said encoded data stream comprises refinement data, the method further comprising:
obtaining refinement data from said decoding device having received and decoded said encoded data stream;
modifying the synthesis data with said refinement data so as to obtain at least one refined depth map part as said synthesis data; and
synthesizing at least one image of an intermediate view being from the modified synthesis data.
10. An apparatus comprising a processing device for processing multi-view video data, wherein the processing device comprises:
a processor and a memory configured to:
obtain at least one part of a decoded texture image of at least one view of the multi-view video, from a decoding device that has received and decoded an encoded data stream representative of the multi-view video, the encoded data stream containing no depth map data,
extract at least one part of a depth map from at least said one part of the decoded texture image, referred to as synthesis data, and
synthesize at least one image of an intermediate view of the multi-view video not encoded in said encoded data stream, from at least said one part of the decoded texture image and from said synthesis data obtained.
11. A terminal comprising the processing device according to claim 10 .
12. The apparatus according to claim 10 , wherein the apparatus comprises the decoding device.
13. A non-transitory computer-readable storage medium, comprising instructions of a computer program which when executed by a processor of a processing device configure the processing device to implement a method for processing multi-view video data, comprising:
obtaining at least one part of a decoded texture image of at least one view of the multi-view video, from a decoding device that has received and decoded an encoded data stream representative of the multi-view video, the encoded data stream containing no depth map data,
extracting at least one part of a depth map from at least said one part of the decoded texture image, referred to as synthesis data, and
synthesizing at least one image of an intermediate view of the multi-view video not encoded in said encoded data stream, from at least said one part of the decoded texture image and from said synthesis data obtained.