Hybrid video coding supporting intermediate view synthesis
Hybrid video decoder supporting intermediate view synthesis of an intermediate view video from a first- and a second-view video which are predictively coded into a multi-view data signal with frames of the second-view video being spatially subdivided into sub-regions and the multi-view data signal having a prediction mode is provided, having: an extractor configured to respectively extract, from the multi-view data signal, for sub-regions of the frames of the second-view video, a disparity vector and a prediction residual; a predictive reconstructor configured to reconstruct the sub-regions of the frames of the second-view video, by generating a prediction from a reconstructed version of a portion of frames of the first-view video using the disparity vectors and a prediction residual for the respective sub-regions; and an intermediate view synthesizer configured to reconstruct first portions of the intermediate view video.
1. A decoder for decoding multi-view data, comprising:
an extractor configured to:
receive multi-view data comprising data related to a first-view video and a second-view video, and
obtain, from the multi-view data, a disparity vector and a prediction residual associated with a sub-region of a frame of the second-view video, wherein the disparity vector indicates a displacement of the sub-region of the frame of the second-view video with respect to a frame of the first-view video;
a predictive reconstructor configured to reconstruct the sub-region of the frame of the second-view video based on a reconstructed portion of the frame of the first-view video, the disparity vector, and the prediction residual, wherein the reconstructed portion of the frame of the first-view video is obtained based on a prediction mode indicated in the data stream; and
a view synthesizer configured to:
determine a scaled disparity vector based on the disparity vector and a scaling factor, and
reconstruct a portion of a frame of a third-view video using the reconstructed portion of the frame of the first view video and the scaled disparity vector.
2. The decoder of claim 1 , wherein the scaling factor is a value between 0 and 1, and the view synthesizer is configured to multiply the disparity vector with the scaling factor to determine the scaled disparity vector.
3. The decoder of claim 1 , wherein the scaling factor is a value less than 0 or greater than 1, and the view synthesizer is configured to multiply the disparity vector with the scaling factor to determine the scaled disparity vector.
4. The decoder of claim 1 , wherein the scaling factor depends on a spatial location of a third view corresponding to the third-view video relative to a first view corresponding to the first-view video and a second view corresponding to the second-view video.
5. The decoder of claim 1 , wherein the scaled disparity vector and the disparity vector are equal.
6. The decoder of claim 1 , wherein the view synthesizer is further configured to extrapolate or interpolate another portion of the frame of the third-view video based on the reconstructed portion of the frame of the third-view video.
7. The decoder of claim 1 , wherein the view synthesizer is further configured to: determine an interpolated disparity vector based on a plurality of disparity vectors associated with different sub-regions of the second-view video, and reconstruct another portion of the frame of the third-view video using the reconstructed portion of the frame of the first view video and the interpolated disparity vector.
8. The decoder of claim 7 , wherein the different sub-regions of the second-view video belong to a same frame of the second-view video.
9. The decoder of claim 7 , wherein the different sub-regions of the second-view video belong to different frames of the second-view video.
10. The decoder of claim 1 , wherein the extractor is further configured to extract, from the multi-view data, reliability data indicating a reliability factor for the disparity vector, wherein the view synthesizer is configured to reconstruct the portion of the frame of the third-view video based on the reliability data satisfying a predetermined requirement.
11. An encoder for encoding multi-view data, comprising:
a prediction unit configured to encode multi-view data comprising data related to a first-view video and a second-view video, the data including a prediction mode used to encode the first-view video,
wherein to encode the multi-view data, the prediction unit is at least configured to determine a disparity vector and a prediction residual associated with a sub-region of a frame of the second-view video, the disparity vector indicating a displacement of the sub-region of the frame of the second-view video with respect to a frame of the first-view video; and
a data signal generator configured to insert the multi-view data including the disparity vector and the prediction residual into a data stream, wherein data associated with a portion of the frame of the first-view video and a scaled disparity vector are used to synthesize a portion of a frame of a third-view video, and the scaled disparity vector is determined using the disparity vector and a scaling factor.
12. The encoder of claim 11 , wherein the scaling factor is a value between 0 and 1, and the scaled disparity vector is determined by multiplying the disparity vector with the scaling factor.
13. The encoder of claim 11 , wherein the scaling factor is a value less than 0 or greater than 1, and the scaled disparity vector is determined by multiplying the disparity vector with the scaling factor.
14. The encoder of claim 11 , wherein the scaling factor depends on a spatial location of a third view corresponding to the third-view video relative to a first view corresponding to the first-view video and a second view corresponding to the second-view video.
15. The encoder of claim 11 , wherein the synthesized portion of the frame of the third view video is used to extrapolate or interpolate another portion of the frame of the third-view video.
16. The encoder of claim 11 , wherein an interpolated disparity vector is determined based on a plurality of disparity vectors associated with different sub-regions of the second-view video, and another portion of the frame of the third-view video is synthesized using the synthesized portion of the frame of the first view video and the interpolated disparity vector.
17. The encoder of claim 16 , wherein the different sub-regions of the second-view video belong to a same frame of the second-view video.
18. The encoder of claim 16 , wherein the different sub-regions of the second-view video belong to different frames of the second-view video.
19. The encoder of claim 11 , wherein the prediction unit is further configured to encode, as part of the multi-view data, reliability data indicating a reliability factor for the disparity vector, wherein the portion of the frame of the third-view video is synthesized based on the reliability data satisfying a predetermined requirement.
20. A non-transitory computer-readable medium for storing data associated with a video, comprising:
a data stream stored in the non-transitory computer-readable medium, the data stream comprising multi-view data including at least a first-view video and a second-view video, the multi-view data comprising a prediction mode used to encode the first-view video, and a disparity vector and a prediction residual associated with a sub-region of a frame of the second-view video, wherein the disparity vector indicates a spatial displacement of the sub-region of the frame of the second-view video with respect to a frame of the first-view video,
wherein data associated with a portion of the frame of the first-view video and a scaled disparity vector are used to synthesize a portion of a frame of a third-view video, and the scaled disparity vector is determined using the disparity vector and a scaling factor.