Salvato in:
| Autori principali: | , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2024
|
| Soggetti: | |
| Accesso online: | https://arxiv.org/abs/2409.19429 |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866916439636574208 |
|---|---|
| author | Chen, Hao Xie, Saining Lim, Ser-Nam Shrivastava, Abhinav |
| author_facet | Chen, Hao Xie, Saining Lim, Ser-Nam Shrivastava, Abhinav |
| contents | Despite the abundant availability and content richness for video data, its high-dimensionality poses challenges for video research. Recent advancements have explored the implicit representation for videos using neural networks, demonstrating strong performance in applications such as video compression and enhancement. However, the prolonged encoding time remains a persistent challenge for video Implicit Neural Representations (INRs). In this paper, we focus on improving the speed of video encoding and decoding within implicit representations. We introduce two key components: NeRV-Enc, a transformer-based hyper-network for fast encoding; and NeRV-Dec, a parallel decoder for efficient video loading. NeRV-Enc achieves an impressive speed-up of $\mathbf{10^4\times}$ by eliminating gradient-based optimization. Meanwhile, NeRV-Dec simplifies video decoding, outperforming conventional codecs with a loading speed $\mathbf{11\times}$ faster, and surpassing RAM loading with pre-decoded videos ($\mathbf{2.5\times}$ faster while being $\mathbf{65\times}$ smaller in size). |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2409_19429 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Fast Encoding and Decoding for Implicit Video Representation Chen, Hao Xie, Saining Lim, Ser-Nam Shrivastava, Abhinav Computer Vision and Pattern Recognition Despite the abundant availability and content richness for video data, its high-dimensionality poses challenges for video research. Recent advancements have explored the implicit representation for videos using neural networks, demonstrating strong performance in applications such as video compression and enhancement. However, the prolonged encoding time remains a persistent challenge for video Implicit Neural Representations (INRs). In this paper, we focus on improving the speed of video encoding and decoding within implicit representations. We introduce two key components: NeRV-Enc, a transformer-based hyper-network for fast encoding; and NeRV-Dec, a parallel decoder for efficient video loading. NeRV-Enc achieves an impressive speed-up of $\mathbf{10^4\times}$ by eliminating gradient-based optimization. Meanwhile, NeRV-Dec simplifies video decoding, outperforming conventional codecs with a loading speed $\mathbf{11\times}$ faster, and surpassing RAM loading with pre-decoded videos ($\mathbf{2.5\times}$ faster while being $\mathbf{65\times}$ smaller in size). |
| title | Fast Encoding and Decoding for Implicit Video Representation |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2409.19429 |