Research map / Video / Video segmentation and tracking
Hierarchical B-Frame Video Coding Using Two-Layer CANF Without Motion Coding
David Alexandre, Hsueh-Ming Hang, Wen-Hsiao Peng
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| Use a two-layer low-resolution base and full-resolution enhancement codec without transmitting motion information | TLZMC · UVG and HEVC Class B | PSNR | Improved |
| Use a two-layer codec without motion coding instead of B-CANF | TLZMC · UVG and HEVC Class B | MS-SSIM | Hurt |
| Add frame-type adaptive coding (ablation) | TLZMC · UVG and HEVC Class B | rate-distortion performance | Improved |
| Add a low-resolution base layer to convey unpredictable-pixel information | TLZMC · B-frame video coding | rate-distortion performance | Improved |
| Remove skip-mask coding (ablation) | TLZMC · UVG, GOP=32 | BD-rate saving: -42.39 vs -35.87 | Hurt |
| Add predicted motion fields and merged image as skip-mask inputs (ablation) | TLZMC skip-mask generator · UVG, GOP=32 | BD-rate saving: -35.87 -> -38.12 | Improved |
| Add hyperprior μ and σ as skip-mask inputs (ablation) | TLZMC skip-mask generator · UVG, GOP=32 | BD-rate saving: -35.87 -> -39.74 | Improved |
| Combine motion/merged-image clues with hyperprior clues for skip-mask generation (ablation) | TLZMC skip-mask generator · UVG, GOP=32 | BD-rate saving: -38.12 and -39.74 -> -42.39 | Improved |
| Increase λ, allowing more latent samples to be retained | TLZMC MSE model · UVG | retained latent samples: 28.28%, 36.23%, 57.17%, and 69.93% | Improved |
| Use GOP=32 rather than GOP=8 (ablation) | TLZMC · UVG | BD-rate saving | Improved |
| Replace the multi-frame merging network with frame synthesis (ablation) | TLZMC · B-frame video coding | rate-distortion performance | Improved |
| Use TLZMC instead of B-CANF | B-frame video coding · UVG, GOP=32 | encode MACs: 2.70M/px -> 1.50M/px | Improved |
Closest papers by meaning
- CANF-VC: Conditional Augmented Normalizing Flows for Video Compression (ECCV 2022 · similarity 0.90)
- Learned Video Compression (ICCV 2019 · similarity 0.87)
- Learning for Video Compression With Hierarchical Quality and Recurrent Enhancement (CVPR 2020 · similarity 0.87)
- Conditional Entropy Coding for Efficient Video Compression (ECCV 2020 · similarity 0.87)
- Neural B-frame Video Compression with Bi-directional Reference Harmonization (NeurIPS 2025 · similarity 0.84)
- Offline and Online Optical Flow Enhancement for Deep Video Compression (AAAI 2024 · similarity 0.84)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.
