Research map / Video / Video segmentation and tracking
HNeRV: A Hybrid Neural Representation for Videos
Read the paperCheck your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (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 learnable content-adaptive frame embeddings and the HNeRV decoder | Video regression · Bunny, 0.75M parameters, 300 epochs | PSNR: 28.46 -> 32.81 | Helped |
| Use learnable content-adaptive frame embeddings and the HNeRV decoder | Video regression · UVG and DAVIS, 960×1920 | PSNR: 29.94 -> 31.49 | Helped |
| Use learnable content-adaptive embeddings | HNeRV · UVG held-out-frame internal generalization | PSNR: 22.82 -> 26.15 | Helped |
| Use HNeRV for video inpainting | HNeRV · UVG, 5 fixed box masks | PSNR: 31.14 -> 32.03 | Helped |
| Use HNeRV instead of IIVI | Video inpainting · UVG, 5 fixed box masks | PSNR: 32.97 -> 32.03 | Hurt |
| Use the HNeRV decoder instead of H.264 | Bunny decoding at PSNR 35 · Bunny | FPS: 240.9 -> 332.7 | Helped |
| Use HNeRV with larger later-layer kernels and wider channels (ablation) | HNeRV · Bunny regression, parameter distribution | PSNR: 29.91 -> 35.57 | Helped |
| Set Kmax to 3 instead of 5 (ablation) | HNeRV · Bunny kernel-size ablation | PSNR: 35.57 -> 35.02 | Hurt |
| Set Kmax to 7 instead of 5 (ablation) | HNeRV · Bunny kernel-size ablation | PSNR: 35.57 -> 35.07 | Hurt |
| Set channel reduction r to 1 instead of 1.2 (ablation) | HNeRV · Bunny channel-reduction ablation | PSNR: 35.57 -> 34.96 | Hurt |
| Set channel reduction r to 1.5 instead of 1.2 (ablation) | HNeRV · Bunny channel-reduction ablation | PSNR: 35.57 -> 34.98 | Hurt |
| Set channel reduction r to 2 instead of 1.2 (ablation) | HNeRV · Bunny channel-reduction ablation | PSNR: 35.57 -> 34.32 | Hurt |
Closest papers by meaning
- Combining Frame and GOP Embeddings for Neural Video Representation (CVPR 2024 · similarity 0.89)
- Boosting Neural Representations for Videos with a Conditional Decoder (CVPR 2024 · similarity 0.88)
- DS-NeRV: Implicit Neural Video Representation with Decomposed Static and Dynamic Codes (CVPR 2024 · similarity 0.88)
- PNeRV: Enhancing Spatial Consistency via Pyramidal Neural Representation for Videos (CVPR 2024 · similarity 0.88)
- MetaNeRV: Meta Neural Representations for Videos with Spatial-Temporal Guidance (AAAI 2025 · similarity 0.88)
- CoANeRV: Coordinate-Aware Token-Space Neural Video Representation (NeurIPS 2026 · similarity 0.86)
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.