HiNeRV: Video Compression with Hierarchical Encoding based Neural Representation
Dec 10, 2023
Speakers
Ho Man Kwan
Speaker · 0 followers
Andrew Gower
Speaker · 0 followers
David Bull
Speaker · 0 followers
About
Learning-based video compression is currently one of the most popular research topics, offering the potential to compete with conventional standard video codecs. In this context, Implicit Neural Representations (INRs) have previously been used to represent and compress image and video content, demonstrating relatively high decoding speed compared to other methods. However, existing INR-based methods have failed to deliver rate quality performance comparable with the state of the art in video compression. This is mainly due to the simplicity of the employed network architectures, which limit their representation capability. In this paper, we propose HiNeRV, an INR that combines bilinear interpolation with novel hierarchical positional encoding. This structure employs depth-wise convolutional and MLP layers to build a deep and wide network architecture with much higher capacity. We further build a video codec based on HiNeRV and a refined pipeline for training, pruning and quantization that can better preserve HiNeRV's performance during lossy model compression. The proposed method has been evaluated on both UVG and MCL-JCV datasets for video compression, demonstrating significant improvement over all existing INRs baselines and competitive performance when compared to learning-based codecs (72.3% overall bit rate saving over HNeRV and 43.4% over DCVC on the UVG dataset, measured in PSNR).Learning-based video compression is currently one of the most popular research topics, offering the potential to compete with conventional standard video codecs. In this context, Implicit Neural Representations (INRs) have previously been used to represent and compress image and video content, demonstrating relatively high decoding speed compared to other methods. However, existing INR-based methods have failed to deliver rate quality performance comparable with the state of the art in video com…
Organizer
NeurIPS 2023
Account · 623 followers
Like the format? Trust SlidesLive to capture your next event!
Professional recording and live streaming, delivered globally.
Sharing
Recommended Videos
Presentations on similar topic, category or speaker
Self-Supervised Reinforcement Learning that Transfers using Random Features
Watch later
Boyuan Chen, …
Total of 0 viewers voted for saving the presentation to eternal vault which is 0.0%
Score-based CRL from Interventions
Watch later
Burak Varıcı, …
Total of 0 viewers voted for saving the presentation to eternal vault which is 0.0%
Statistically Valid Variable Importance Assessment through Conditional Permutations
Watch later
Ahmad Chamma, …
Total of 0 viewers voted for saving the presentation to eternal vault which is 0.0%
Why think step by step? Reasoning emerges from the locality of experience
Watch later
Total of 0 viewers voted for saving the presentation to eternal vault which is 0.0%
k-Means Clustering with Distance-Based Privacy
Watch later
Total of 0 viewers voted for saving the presentation to eternal vault which is 0.0%
Robust Learning for Smoothed Online Convex Optimization with Feedback Delay
Watch later
Pengfei Li, …
Total of 0 viewers voted for saving the presentation to eternal vault which is 0.0%