AIVC: Artificial Intelligence based Video Codec
Not on the map. Why?
Abstract (arXiv)
This paper introduces AIVC, an end-to-end neural video codec. It is based on two conditional autoencoders MNet and CNet, for motion compensation and coding. AIVC learns to compress videos using any coding configurations through a single end-to-end rate-distortion optimization. Furthermore, it offers performance competitive with the recent video coder HEVC under several established test conditions. A comprehensive ablation study is performed to evaluate the benefits of the different modules composing AIVC. The implementation is made available at https://orange-opensource.github.io/AIVC/.
Key facts. Cited by 6 papers in the map (data through 7 Oct 2026). First posted on arXiv 9 Feb 2022.
Builds on
No reference list yet.
Built on by
Citing papers per year: 2022: 1; 2023: 3; 2024: 1; 2025: 1.
6 papers.
- 2023Video Event Restoration Based on Keyframes for Video Anomaly Detectioncited by 54
- 2023IBVC: Interpolation-driven B-frame Video Compressioncited by 12
- 2023Latent-Shift: Gradient of Entropy Helps Neural Codecscited by 3
- 2022Reducing The Mismatch Between Marginal and Learned Distributions in Neural Video Compressioncited by 2
- 2024NN-VVC: Versatile Video Coding boosted by self-supervisedly learned image coding for machinescited by 1
- 2025Exploiting Latent Properties to Optimize Neural Codecscited by 0
- 2025Exploiting Latent Properties to Optimize Neural Codecs2 Jan 2025
- 2024NN-VVC: Versatile Video Coding boosted by self-supervisedly learned image coding for machines19 Jan 2024
- 2023IBVC: Interpolation-driven B-frame Video Compression25 Sep 2023
- 2023Latent-Shift: Gradient of Entropy Helps Neural Codecs1 Aug 2023
- 2023Video Event Restoration Based on Keyframes for Video Anomaly Detection11 Apr 2023
- 2022Reducing The Mismatch Between Marginal and Learned Distributions in Neural Video Compression12 Oct 2022