Research map / Probabilistic and scientific modeling / Variational and generative sampling
Bit Allocation using Optimization
Tongda Xu, Han Gao, Chenjian Gao, Yuanyuan Wang, Dailan He, Jinyong Pi, Jixiang Luo, Ziyu Zhu, Mao Ye, Hongwei Qin, Yan Wang, Jingjing Liu and 1 more
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 proposed pixel-level SAVI bit allocation instead of OEU | DVC and DCVC · HEVC Class D | BD-PSNR: DVC: 0.83 -> 1.67 dB; DCVC: 0.74 -> 1.55 dB | Improved |
| Replace Proposed-Approx with the scalable approximation (ablation) | DVC · HEVC Class D | BD-BR: -35.86% -> -29.81% | Hurt |
| Use scalable approximation instead of Proposed-Approx (ablation) | DVC · HEVC Class D | encoding time: 528.3s -> 74.6s | Improved |
| Optimize each frame independently rather than using GoP-level optimization (ablation) | Original SAVI on DVC · HEVC Class D | BD-BR: Original SAVI: -14.76%; Original SAVI (per-frame): -20.12% | Improved |
| Reduce gradient-ascent steps from 2000 to 1000 (ablation) | Proposed-Scalable on DVC · HEVC Class D | BD-BR: -29.81 -> -25.37 | Hurt |
| Reduce gradient-ascent steps from 2000 to 500 (ablation) | Proposed-Approx on DVC · HEVC Class D | BD-BR: -35.86 -> -25.60 | Hurt |
| Use Original SAVI instead of FAVI initialization alone (ablation) | 2-level VAE · MNIST | NLL lowerbound: ≤ 98.3113 -> ≤ 91.5530 | Improved |
| Use proposed approximate SAVI instead of Original SAVI (ablation) | 2-level VAE · MNIST | NLL lowerbound: ≤ 91.5530 -> ≤ 91.5486 | Improved |
| Use accurate SAVI rather than approximate SAVI (ablation) | 2-level VAE · MNIST | NLL lowerbound: ≤ 91.5486 -> ≤ 91.5482 | Improved |
| Restrict gradient likelihood evaluation to C future frames (ablation) | Proposed-Scalable · NVC | RAM scaling with GoP size | Improved |
Closest papers by meaning
- Reinforced Rate Control for Neural Video Compression via Inter-Frame Rate–Distortion Awareness (AAAI 2026 · similarity 0.87)
- Neural Video Compression with Feature Modulation (CVPR 2024 · similarity 0.87)
- Towards Practical Real-Time Neural Video Compression (CVPR 2025 · similarity 0.86)
- On Quantizing Neural Representation for Variable-Rate Video Coding (ICLR 2025 · similarity 0.85)
- Towards Lossless Implicit Neural Representation via Bit Plane Decomposition (CVPR 2025 · similarity 0.85)
- Robustly overfitting latents for flexible neural image compression (NeurIPS 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.
