NeRV: Neural Representations for Videos Supplementary Material Hao Chen

We provide the architecture details in Table 1. A.3 Implementation Details of Baselines Following prior works, we used ffmpeg [2] to produce the evaluation metrics for H.264 and HEVC. Then we use the following commands to compress videos with H.264 or HEVC codec under medium We also explore NeRV for video temporal interpolation task. We provide denoising results on'ig buck bunny' video in Figure 3. NeRV can reconstruct the original video with high fidelity. We test a smaller model on "Bosphorus" video, and it also has As the most popular media format nowadays, videos are generally viewed as frames of sequences.