Timezone: »
In modern video encoders, rate control is a critical component and has been heavily engineered. It decides how many bits to spend to encode each frame, in order to optimize the rate-distortion trade-off over all video frames. This is a challenging constrained planning problem because of the complex dependency among decisions for different video frames and the bitrate constraint defined at the end of the episode.
We formulate the rate control problem as a Partially Observable Markov Decision Process (POMDP), and apply imitation learning to learn a neural rate control policy. We demonstrate that by learning from optimal video encoding trajectories obtained through evolution strategies, our learned policy achieves better encoding efficiency and has minimal constraint violation. In addition to imitating the optimal actions, we find that additional auxiliary losses, data augmentation/refinement and inference-time policy improvements are critical for learning a good rate control policy. We evaluate the learned policy against the rate control policy in libvpx, a widely adopted open source VP9 codec library, in the two-pass variable bitrate (VBR) mode. We show that over a diverse set of real-world videos, our learned policy achieves 8.5% median bitrate reduction without sacrificing video quality.
Author Information
Hongzi Mao (MIT CSAIL)
Chenjie Gu (DeepMind)
Miaosen Wang (Google)
Angie Chen (Google)
Nevena Lazic (DeepMind)
Nir Levine (Deepmind)
Derek Pang (Google)
Rene Claus (Google)
Marisabel Hechtman (Google)
Ching-Han Chiang (Google Inc.)
Cheng Chen (Google Inc.)
Jingning Han (Google Inc.)
More from the Same Authors
-
2021 Poster: Improved Regret Bound and Experience Replay in Regularized Policy Iteration »
Nevena Lazic · Dong Yin · Yasin Abbasi-Yadkori · Csaba Szepesvari -
2021 Oral: Improved Regret Bound and Experience Replay in Regularized Policy Iteration »
Nevena Lazic · Dong Yin · Yasin Abbasi-Yadkori · Csaba Szepesvari -
2019 Poster: POLITEX: Regret Bounds for Policy Iteration using Expert Prediction »
Yasin Abbasi-Yadkori · Peter Bartlett · Kush Bhatia · Nevena Lazic · Csaba Szepesvari · Gellért Weisz -
2019 Oral: POLITEX: Regret Bounds for Policy Iteration using Expert Prediction »
Yasin Abbasi-Yadkori · Peter Bartlett · Kush Bhatia · Nevena Lazic · Csaba Szepesvari · Gellért Weisz -
2019 Poster: Graph Matching Networks for Learning the Similarity of Graph Structured Objects »
Yujia Li · Chenjie Gu · Thomas Dullien · Oriol Vinyals · Pushmeet Kohli -
2019 Oral: Graph Matching Networks for Learning the Similarity of Graph Structured Objects »
Yujia Li · Chenjie Gu · Thomas Dullien · Oriol Vinyals · Pushmeet Kohli -
2018 Poster: Online Linear Quadratic Control »
Alon Cohen · Avinatan Hasidim · Tomer Koren · Nevena Lazic · Yishay Mansour · Kunal Talwar -
2018 Oral: Online Linear Quadratic Control »
Alon Cohen · Avinatan Hasidim · Tomer Koren · Nevena Lazic · Yishay Mansour · Kunal Talwar