Research map / Video / Video segmentation and tracking
NIRVANA: Neural Implicit Representations of Videos With Adaptive Networks and Autoregressive Patch-Wise Modeling
Shishira R. Maiya, Sharath Girish, Max Ehrlich, Hanyu Wang, Kwot Sin Lee, Patrick Poirson, Pengxiang Wu, Chen Wang, Abhinav Shrivastava
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 patch-wise autoregressive modeling instead of pixel-wise SIREN | Video INR compression · UVG-HD | PSNR: 27.20 -> 34.71 | Improved |
| Use patch-wise autoregressive modeling instead of frame-wise NeRV | Video INR compression · UVG-HD | encoding time (hours): ∼80 -> 6.71 | Improved |
| Use patch-wise autoregressive modeling instead of frame-wise NeRV | Video INR compression · UVG-HD | PSNR: 37.36 -> 37.70 | Improved |
| Use NIRVANA instead of NeRV | Video INR compression · UVG-4K | encoding time (hours): ∼134 -> 20.89 | Improved |
| Use NIRVANA instead of NeRV | Video INR compression · UVG-4K | PSNR: 35.24 -> 35.18 | Hurt |
| Use NIRVANA rather than a fixed-size NeRV model as video duration grows | Video INR compression · YouTube-8M Mario Kart, 2000/3000/4000 frames | PSNR: 33.38 -> 31.6 -> 30.53 (NeRV); NIRVANA: 35.43, 35.21, 35.15 | Improved |
| Increase entropy regularization coefficient (ablation) | NIRVANA · Jockey, UVG-HD | BPP | Improved |
| Increase entropy regularization coefficient (ablation) | NIRVANA · Jockey, UVG-HD | PSNR | Hurt |
| Increase patch size (ablation) | NIRVANA · Jockey, UVG-HD | PSNR | Improved |
| Increase patch size (ablation) | NIRVANA · Jockey, UVG-HD | BPP | Hurt |
| Increase frame group size (ablation) | NIRVANA · Jockey, UVG-HD | BPP | Improved |
| Increase frame group size (ablation) | NIRVANA · Jockey, UVG-HD | PSNR | Hurt |
Later papers that compared with this method
1 later accepted paper reports NIRVANA as a baseline in their results tables; 1 of them report a better number on most of the results they share with it.
- Latent-INR: A Flexible Framework for Implicit Representations of Videos with Discriminative Semantics (ECCV 2024 · 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 1 on most shared results.
- NeRV — NeRV: Neural Representations for Videos (NeurIPS 2021) · better on 6 of 7 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
- Combining Frame and GOP Embeddings for Neural Video Representation (CVPR 2024 · similarity 0.88)
- NVRC: Neural Video Representation Compression (NeurIPS 2024 · similarity 0.87)
- Boosting Neural Representations for Videos with a Conditional Decoder (CVPR 2024 · similarity 0.87)
- Neural Video Compression with Feature Modulation (CVPR 2024 · similarity 0.87)
- Bias for Action: Video Implicit Neural Representations with Bias Modulation (CVPR 2025 · similarity 0.86)
- On Quantizing Neural Representation for Variable-Rate Video Coding (ICLR 2025 · 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.
