Manish Kumar Singh
Manish Kumar Singh has a total of 10 co-authors. Here are the top co-authors by number of shared publications:
- Amir Said
Qualcomm AI Research
1 shared publication - Fatih Porikli
Qualcomm AI Research
1 shared publication - Hong Cai
Qualcomm AI Research
1 shared publication - Jisoo Jeong
Qualcomm AI Research
1 shared publication - Rajeev Yasarla
Qualcomm AI Research
1 shared publication - Reza Pourreza
Qualcomm AI Research
1 shared publication
Latest Publications
- 30 October 2024
- Published by Springer Nature
- p. 440-458
FutureDepth: Learning to Predict the Future Improves Video Depth Estimation
- 30 October 2024
- Published by Springer Nature
- p. 440-458
FutureDepth: Learning to Predict the Future Improves Video Depth Estimation
- Open Access
Differentiable bit-rate estimation for neural-based video codec enhancement
Neural networks (NN) can improve standard video compression by pre- and post-processing the encoded video. For optimal NN training, the standard codec needs to be replaced with a codec proxy that can provide derivatives of estimated bit-rate and distortion, which are used for gradient back-propagation. Since entropy coding of standard codecs is designed to take into account non-linear dependencies between transform coefficients, bit-rates cannot be well approximated with simple per-coefficient estimators. This paper presents a new approach for bit-rate estimation that is similar to the type employed in training end-to-end neural codecs, and able to efficiently take into account those statistical dependencies. It is defined from a mathematical model that provides closed-form formulas for the estimates and their gradients, reducing the computational complexity. Experimental results demonstrate the method's accuracy in estimating HEVC/H.265 codec bit-rates.
Open AccessDifferentiable bit-rate estimation for neural-based video codec enhancement
Neural networks (NN) can improve standard video compression by pre- and post-processing the encoded video. For optimal NN training, the standard codec needs to be replaced with a codec proxy that can provide derivatives of estimated bit-rate and distortion, which are used for gradient back-propagation. Since entropy coding of standard codecs is designed to take into account non-linear dependencies between transform coefficients, bit-rates cannot be well approximated with simple per-coefficient estimators. This paper presents a new approach for bit-rate estimation that is similar to the type employed in training end-to-end neural codecs, and able to efficiently take into account those statistical dependencies. It is defined from a mathematical model that provides closed-form formulas for the estimates and their gradients, reducing the computational complexity. Experimental results demonstrate the method's accuracy in estimating HEVC/H.265 codec bit-rates.