Research map / Architectures and efficiency / Quantization
NVTC: Nonlinear Vector Transform Coding
Runsen Feng, Zongyu Guo, Weiping Li, Zhibo Chen
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 entropy-constrained VQ rather than nonlinear transform coding with scalar quantization | Toy-source quantization · Isotropic Gaussian 2d, 4d, 8d, and 16d | BD-PSNR (dB): -0.15, -0.31, -0.47, and -0.71 BD-PSNR for NTC over ECVQ | Improved |
| Use entropy-constrained VQ rather than nonlinear transform coding with scalar quantization | Toy-source quantization · IG, Banana, and Boomerang | BD-PSNR (dB): -0.15, -0.21, and -0.58 BD-PSNR for NTC over ECVQ | Improved |
| Replace VT with convolutional resblocks (ablation) | NVTC · CLIC 2021 validset | BD-rate: 0.0% -> 7.3% | Hurt |
| Replace ECVQ with unconstrained VQ (ablation) | NVTC · CLIC 2021 validset | BD-rate: 0.0% -> 23.9% | Hurt |
| Use random initialization instead of progressive initialization (ablation) | NVTC · CLIC 2021 validset | BD-rate: 0.0% -> 17.1% | Hurt |
| Reduce quantization-layer groups to L=3+3+2 (ablation) | NVTC · Kodak | BD-rate: 0.0% -> 7.7% | Hurt |
| Remove the first quantization-layer group, using L=0+6+4 (ablation) | NVTC · Kodak | BD-rate: 0.0% -> 6.8% | Hurt |
| Use only the final quantization-layer group, L=0+0+4 (ablation) | NVTC · Kodak | BD-rate: 0.0% -> 27.1% | Hurt |
| Replace Depth-wise Block FC with Block FC (ablation) | NVTC · Kodak | BD-rate: 0.0% -> 29.4% | Hurt |
| Replace CEM with an unconditional entropy model in entropy coding (ablation) | NVTC · Kodak | BD-rate: 0.0% -> 39.6% | Hurt |
| Use NVTC rather than Zhu-CVPR2022 | Learned image compression · CLIC2021 validset | BD-rate: -10.9% | Improved |
Later papers that compared with this method
1 later accepted paper reports NVTC as a baseline in their results tables; 1 of them report a better number on most of the results they share with it.
- Approaching Rate-Distortion Limits in Neural Compression with Lattice Transform Coding (ICLR 2025 · better on 2 of 2 shared results)
Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.
Closest papers by meaning
- Learning Optimal Lattice Vector Quantizers for End-to-end Neural Image Compression (NeurIPS 2024 · similarity 0.90)
- Approaching Rate-Distortion Limits in Neural Compression with Lattice Transform Coding (ICLR 2025 · similarity 0.88)
- On Quantizing Neural Representation for Variable-Rate Video Coding (ICLR 2025 · similarity 0.88)
- NVRC: Neural Video Representation Compression (NeurIPS 2024 · similarity 0.88)
- Multirate Neural Image Compression with Adaptive Lattice Vector Quantization (CVPR 2025 · similarity 0.87)
- Neural Video Compression with Feature Modulation (CVPR 2024 · similarity 0.87)
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.
