Signaling duplicated vertices removal in mesh motion vector coding
A method of decoding a dynamic mesh sequence, the method includes: receiving a coded bitstream comprising the dynamic mesh sequence in a first frame and a second frame that occurs later than the first frame; reconstructing the dynamic mesh in the first frame; determining whether a duplicate vertex removal mode is enabled in which a motion vector of a vertex in the dynamic mesh second that is a duplicate of a vertex in the dynamic mesh sequence in the first frame; based on determining that the duplicate vertex removal mode is enabled, decoding a motion vector for each vertex in the second frame that is not a duplicate of a vertex in the reconstructed first frame; and reconstruct the dynamic mesh sequence in the second frame using the reconstructed dynamic mesh in the first frame and each decoded motion vector.
1 . A method of decoding a dynamic mesh sequence, the method comprising:
receiving a coded bitstream comprising the dynamic mesh sequence in a first frame and a second frame that occurs later than the first frame;
reconstructing the dynamic mesh in the first frame;
determining, based on a statistical calculation performed to determine a percentage of vertices that are in the reconstructed first frame, whether a duplicate vertex removal mode is enabled in which a motion vector of a vertex in the dynamic mesh second that is a duplicate of a vertex in the dynamic mesh sequence in the first frame;
based on determining that the duplicate vertex removal mode is enabled, decoding a motion vector for each vertex in the second frame that is not a duplicate of a vertex in the reconstructed first frame; and
reconstruct the dynamic mesh sequence in the second frame using the reconstructed dynamic mesh in the first frame and each decoded motion vector.
2 . The method according to claim 1 , wherein the duplicate vertex removal mode is enabled based on a determination that a percentage of duplicate vertices in the first reference frame is greater than or equal to a threshold.
3 . The method of claim 1 , further comprising:
based on determining that the duplicate vertex removal mode is not enabled, decoding a motion vector for each vertex in the second frame regardless of whether the vertex in the second frame is a duplicate of a vertex in the first frame.
4 . The method of claim 1 , wherein a vertex in the second frame is a duplicate of a vertex in the first frame based on a determination that the vertex in the second frame has the same coordinates as the vertex in the first frame.
5 . The method of claim 1 , wherein the coded video bitstream comprises a flag that indicates that the vertex in the second frame is a duplicate of a vertex in the first frame.
6 . A method of encoding a dynamic mesh sequence, the method comprising:
receiving a first frame comprising the dynamic mesh sequence and a second frame comprising the dynamic mesh sequence, the second frame occurring after the first frame;
determining a motion vector between each vertex of the dynamic mesh sequence in the first frame and a corresponding vertex of the dynamic mesh sequence in the second frame;
generating a coded bitstream that includes each determined motion vector, an indication whether a vertex of the dynamic mesh sequence in the second frame is a duplicate of a vertex of the dynamic mesh sequence in the first frame, and an indication whether a duplicate vertex removal mode is enabled in which a motion vector of a vertex in the dynamic mesh sequence of the second frame that is a duplicate of a vertex in the dynamic mesh sequence in the first frame is skipped in a reconstruction of the second frame; and
setting a flag indicating whether a duplicate removal mode is enabled based on a statistical calculation that determines a percentage of vertices of the dynamic mesh sequence in the first frame and vertices of the dynamic mesh sequence in the second frame that are duplicates, the flag included in the coded bitstream.
7 . The method of claim 6 , wherein the flag is set to enable the duplicate removal mode based on a determination that the percentage of vertices of the dynamic mesh sequence in the first frame and vertices of the dynamic mesh sequence in the second frame that are duplicates is greater than a threshold.
8 . The method according to claim 6 , wherein a motion vector for each vertex in the second frame is decoded based on a determination the duplicate vertex removal mode is not enabled regardless of whether the vertex in the second frame is a duplicate of a vertex in the first frame.
9 . The method of claim 6 , wherein a vertex in the second frame is a duplicate of a vertex in the first frame based on a determination that the vertex in the second frame has the same coordinates as the vertex in the first frame.
10 . The method according to claim 6 , wherein the coded bitstream includes a flag indicating whether a vertex of the dynamic mesh sequence in the second frame is a duplicate of a vertex of the dynamic mesh sequence in the first frame.
11 . A method of processing a dynamic mesh sequence, the method comprising:
reconstructing a dynamic mesh sequence in a second frame that occurs after the first frame based on a coded bitstream that includes the first frame and the second frame,
wherein the first frame is reconstructed,
wherein the coded video bitstream includes an indication of whether a duplicate vertex removal mode is enabled in which a motion vector of a vertex in the dynamic mesh second that is a duplicate of a vertex in the dynamic mesh sequence in the first frame,
wherein determining whether the duplicate vertex removal mode is enabled is based on a statistical calculation performed to determine a percentage of vertices that are in the reconstructed first frame,
wherein based on determining that the duplicate vertex removal mode is enabled, a motion vector for each vertex in the second frame that is not a duplicate of a vertex in the reconstructed first frame is decoded, and
wherein the dynamic mesh sequence in the second frame is reconstructed using the reconstructed first frame and each decoded motion vector.
12 . The method according to claim 11 , wherein the duplicate vertex removal mode is enabled based on a determination that a percentage of duplicate vertices in the first reference frame is greater than or equal to a threshold.
13 . The method of claim 11 , wherein determining whether the duplicate vertex removal mode is enabled is based on a determination that a flag in the coded bitstream indicates that the duplicate vertex removal mode is enabled.
14 . The method of claim 11 , wherein based on determining that the duplicate vertex removal mode is not enabled, a motion vector for each vertex in the second frame is decoded regardless of whether the vertex in the second frame is a duplicate of a vertex in the first frame.
15 . The method of claim 1 , wherein a vertex in the second frame is a duplicate of a vertex in the first frame based on a determination that the vertex in the second frame has the same coordinates as the vertex in the first frame.