Review — DLT: Deep Learning-Based Nonlinear Transform for HEVC Intra Coding (HEVC Intra)

Deep Learning-based Transform (DLT) Using Autoencoder, 0.75% BD-Rate Reduction is Achieved

Overview of the Proposed Deep Learning-Based Transform (DLT)


1. Directionality in Residual Domain

The directional information in the prediction block and the residual block after directional intra prediction.

2. DLT: Network Architecture

Top: Directional Module, Bottom, Transform Module

2.1. Directional Module (Top)

2.2. Transform Module (Bottom)

2.2.1. Encoder for Forward Transform

2.2.2. Decoder for Inverse Transform

3. Loss Function

3.1. L2 Loss

3.2. Energy Compact Loss

3.3. Total Loss

4. Experimental Results

4.1. Training

4.2. BD-Rate

BD-Rate (%) on CTC Test Sequences

4.3. Usage

The red blocks represent the 8×8 TUs that use the proposed DLT instead of the DCT

PhD, Researcher. I share what I've learnt and done. :) My LinkedIn:, My Paper Reading List: