Research map / Video / Video segmentation and tracking
E-NeRV: Expedite Neural Video Representation with Disentangled Spatial-Temporal Context
Zizhang Li, Mengmeng Wang, Huaijin Pi, Kechun Xu, Jianbiao Mei, Yong Liu
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 |
|---|---|---|---|
| add spatial fusion function Phi at network start (ablation) | E-NeRV · 8 videos average | PSNR: 37.89 -> 38.09 | Improved |
| add spatial-temporal fusion F_theta (transformer) (ablation) | E-NeRV · 8 videos average | PSNR: 38.09 -> 38.45 | Improved |
| add temporal instance normalization branch (ablation) | E-NeRV · 8 videos average | PSNR: 38.45 -> 38.79 | Improved |
| disentangle spatial/temporal context and reallocate saved parameters to conv channels (ablation) | NeRV-L · 8 videos average | PSNR: 36.74 -> 37.89 | Improved |
| use transformer instead of MLP for fusion (ablation) | E-NeRV · 8 videos average | PSNR: 38.54 -> 38.79 | Improved |
| use transformer instead of 3x3 conv for fusion (ablation) | E-NeRV · 8 videos average | PSNR: 38.67 -> 38.79 | Improved |
| use disentangled design instead of NeRV-Split at 7.2M | NeRV · 8 videos average | PSNR: 35.78 -> 36.74 | Improved |
| use disentangled design instead of NeRV-C_S at 5.8M | NeRV · 8 videos average | PSNR: 33.72 -> 35.91 | Improved |
| replace NeRV with E-NeRV at similar size | NeRV-L · Bunny video | PSNR: 39.63 -> 42.87 | Improved |
| replace NeRV with E-NeRV at similar size | NeRV-L · Beauty video | PSNR: 36.06 -> 36.72 | Improved |
| replace NeRV with E-NeRV for denoising | NeRV · Video denoising | PSNR: 34.69 -> 36.23 | Improved |
| lower IN frequency b from 1.25 to 1.05 in E-NeRV | E-NeRV · Bunny unseen frames | PSNR: 29.32 -> 33.77 | Improved |
Closest papers by meaning
- Combining Frame and GOP Embeddings for Neural Video Representation (CVPR 2024 · similarity 0.90)
- MetaNeRV: Meta Neural Representations for Videos with Spatial-Temporal Guidance (AAAI 2025 · similarity 0.90)
- DS-NeRV: Implicit Neural Video Representation with Decomposed Static and Dynamic Codes (CVPR 2024 · similarity 0.90)
- PNeRV: Enhancing Spatial Consistency via Pyramidal Neural Representation for Videos (CVPR 2024 · similarity 0.89)
- Boosting Neural Representations for Videos with a Conditional Decoder (CVPR 2024 · similarity 0.87)
- CoANeRV: Coordinate-Aware Token-Space Neural Video Representation (NeurIPS 2026 · similarity 0.85)
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.
