摘要
This paper introduces an online motion rate adaptation scheme for learned video compression, with the aim of
achieving content-adaptive coding on individual test sequences
to mitigate the domain gap between training and test data. It
features a patch-level bit allocation map, termed the α-map, to
trade off between the bit rates for motion and inter-frame coding
in a spatially-adaptive manner. We optimize the α-map through
an online back-propagation scheme at inference time. Moreover,
we incorporate a look-ahead mechanism to consider its impact
on future frames. Extensive experimental results confirm that
the proposed scheme, when integrated into a conditional learned
video codec, is able to adapt motion bit rate effectively, showing
much improved rate-distortion performance particularly on test
sequences with complicated motion characteristics.
achieving content-adaptive coding on individual test sequences
to mitigate the domain gap between training and test data. It
features a patch-level bit allocation map, termed the α-map, to
trade off between the bit rates for motion and inter-frame coding
in a spatially-adaptive manner. We optimize the α-map through
an online back-propagation scheme at inference time. Moreover,
we incorporate a look-ahead mechanism to consider its impact
on future frames. Extensive experimental results confirm that
the proposed scheme, when integrated into a conditional learned
video codec, is able to adapt motion bit rate effectively, showing
much improved rate-distortion performance particularly on test
sequences with complicated motion characteristics.
| 原文 | English |
|---|---|
| 頁面 | 163-167 |
| 頁數 | 5 |
| 出版狀態 | Published - 12月 2022 |
| 事件 | 2022 Picture Coding Symposium, PCS 2022 - San Jose, United States 持續時間: 7 12月 2022 → 9 12月 2022 |
Conference
| Conference | 2022 Picture Coding Symposium, PCS 2022 |
|---|---|
| 國家/地區 | United States |
| 城市 | San Jose |
| 期間 | 7/12/22 → 9/12/22 |