Research map / Video / Video segmentation and tracking
Compact Neural Volumetric Video Representations with Dynamic Codebooks
Haoyu Guo, Sida Peng, Yunzhi Yan, Linzhan Mou, Yujun Shen, Hujun Bao, Xiaowei Zhou
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 codebook compression to feature plane model (ablation) | feature plane model · NHR | PSNR: 32.16 -> 31.52 | Hurt |
| add codebook compression to feature plane model (ablation) | feature plane model · NHR | Size (MB): 91 -> 5.7 | Improved |
| add dynamic codebook on top of compression (ablation) | compressed model · NHR | PSNR: 31.52 -> 32.10 | Improved |
| add dynamic codebook on top of compression (ablation) | compressed model · NHR | SSIM: 0.943 -> 0.947 | Improved |
| add dynamic codebook on top of compression (ablation) | compressed model · NHR | Size (MB): 5.7 -> 16.6 | Hurt |
| add codebook compression to feature plane model (ablation) | feature plane model · DyNeRF dataset | PSNR: 30.56 -> 30.37 | Hurt |
| add codebook compression to feature plane model (ablation) | feature plane model · DyNeRF dataset | Size (MB): 523 -> 22 | Improved |
| add dynamic codebook on top of compression (ablation) | compressed model · DyNeRF dataset | PSNR: 30.37 -> 30.58 | Improved |
| add dynamic codebook on top of compression (ablation) | compressed model · DyNeRF dataset | SSIM: 0.920 -> 0.923 | Improved |
| add dynamic codebook on top of compression (ablation) | compressed model · DyNeRF dataset | Size (MB): 22 -> 27 | Hurt |
| use Ours instead of K-Planes | Ours · NHR | Size (MB): 103 -> 16.6 | Improved |
| use Ours instead of K-Planes | Ours · NHR | PSNR: 31.08 -> 32.10 | Improved |
Closest papers by meaning
- Representing Volumetric Videos As Dynamic MLP Maps (CVPR 2023 · similarity 0.89)
- DaReNeRF: Direction-aware Representation for Dynamic Scenes (CVPR 2024 · similarity 0.85)
- CodecNeRF: Toward Fast Encoding and Decoding, Compact, and High-quality Novel-view Synthesis (AAAI 2025 · similarity 0.85)
- 4D3R: Motion-Aware Neural Reconstruction and Rendering of Dynamic Scenes from Monocular Videos (NeurIPS 2025 · similarity 0.84)
- VRVVC: Variable-Rate NeRF-Based Volumetric Video Compression (AAAI 2025 · similarity 0.84)
- DiVa-360: The Dynamic Visual Dataset for Immersive Neural Fields (CVPR 2024 · similarity 0.84)
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.
