Research map / Video / Video segmentation and tracking
HiNeRV: Video Compression with Hierarchical Encoding-based Neural Representation
Ho Man Kwan, Ge Gao, Fan Zhang, Andy Gower, David Bull
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 HiNeRV instead of prior NeRV-style models | video representation · UVG avg, scale S | PSNR (dB): 32.68 -> 35.27 | Improved |
| HiNeRV vs faster NeRV baselines | Bunny scale S · Bunny | decoding FPS: 202.3 -> 76.7 | Hurt |
| add bilinear upsampling with hierarchical encoding instead of sub-pixel conv 1x1 (ablation) | HiNeRV · UVG ablation | avg PSNR (dB): 34.78 -> 36.27 | Improved |
| use bilinear upsampling instead of sub-pixel conv 3x3 (ablation) | HiNeRV · UVG ablation | avg PSNR (dB): 33.70 -> 36.27 | Improved |
| add hierarchical upsampling encoding (ablation) | HiNeRV · UVG ablation | avg PSNR (dB): 35.95 -> 36.27 | Improved |
| hierarchical encoding instead of Fourier / local Fourier / local grid encoding (ablation) | HiNeRV · UVG ablation | avg PSNR (dB): 35.92/35.77/35.98 -> 36.27 | Improved |
| ConvNeXt block instead of MLP block (ablation) | HiNeRV · UVG ablation | avg PSNR (dB): 34.69 -> 36.27 | Improved |
| ConvNeXt block instead of two conv layers (ablation) | HiNeRV · UVG ablation | avg PSNR (dB): 35.12 -> 36.27 | Improved |
| unified frame/patch representation instead of frame-wise (ablation) | HiNeRV · UVG ablation | avg PSNR (dB): 36.10 -> 36.27 | Improved |
| unified representation instead of patch-wise (ablation) | HiNeRV · UVG ablation | avg PSNR (dB): 35.38 -> 36.27 | Improved |
| bilinear instead of nearest neighbor interpolation (ablation) | HiNeRV · UVG ablation | avg PSNR (dB): 36.08 -> 36.27 | Improved |
| HiNeRV vs conventional/learned codecs on PSNR BD-rate | video compression · UVG | BD-rate PSNR: beats x265, DCVC, VCT; HM RA 7.54% worse anchor | Mixed |
Later papers that compared with this method
2 later accepted papers report HiNeRV as a baseline in their results tables; 2 of them report a better number on most of the results they share with it.
- Enhanced Neural Video Representation Compression with High Scalability (ECCV 2026 · better on 3 of 3 shared results)
- PNVC: Towards Practical INR-based Video Compression (AAAI 2025 · better on 2 of 2 shared results)
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 2 on most shared results.
- HNeRV — HNeRV: A Hybrid Neural Representation for Videos (CVPR 2023) · better on 2 of 2 shared results
- NeRV — NeRV: Neural Representations for Videos (NeurIPS 2021) · better on 1 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
- HNeRV: A Hybrid Neural Representation for Videos (CVPR 2023 · similarity 0.93)
- NVRC: Neural Video Representation Compression (NeurIPS 2024 · similarity 0.91)
- Boosting Neural Representations for Videos with a Conditional Decoder (CVPR 2024 · similarity 0.89)
- Combining Frame and GOP Embeddings for Neural Video Representation (CVPR 2024 · similarity 0.89)
- PNVC: Towards Practical INR-based Video Compression (AAAI 2025 · similarity 0.88)
- 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.
