Research map / Video / Video segmentation and tracking
Beyond Perspective: Neural 360-Degree Video Compression
Andy Regensky, Marc Windsheimer, Fabian Brand, Andre Kaup
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 flow-guided reprojection to training on UGC360 only (ablation) | DCVC-HEM · JVET360 | BD-Rate (%): -2.48 -> -6.98 | Improved |
| add flow-guided reprojection to training on UGC360 only (ablation) | DCVC-HEM · Perspective datasets average | BD-Rate (%): 7.39 -> 2.22 | Improved |
| add flow-guided reprojection to joint training (ablation) | DCVC-HEM-360 · Perspective datasets average | BD-Rate (%): 1.15 -> -3.40 | Improved |
| add vimeo90k to UGC360 training data (ablation) | DCVC-HEM with FGR · Perspective datasets average | BD-Rate (%): 2.22 -> -1.13 | Improved |
| add positional feature encoding to entropy model (DCVC-HEM-360) (ablation) | DCVC-HEM with FGR · Perspective datasets average | BD-Rate (%): -1.13 -> -3.40 | Improved |
| add positional feature encoding to entropy model (DCVC-HEM-360) (ablation) | DCVC-HEM with FGR · JVET360 | BD-Rate (%): -7.12 -> -7.73 | Improved |
| add flow guide to patch sampling (ablation) | DCVC-HEM FGR · JVET360 | BD-Rate (%): +1.35% bitrate without it | Improved |
| use mipmapped bilinear interpolation in reprojection (ablation) | DCVC-HEM FGR · JVET360 | BD-Rate (%): +4.34% bitrate without it | Improved |
| add reprojection on top of flow guide (ablation) | DCVC-HEM-360 · HEVC+UVG | BD-Rate (%): +6.88% bitrate with flow guide only | Improved |
| add positional encoding to entropy model only | DCVC-HEM · Complexity | GMACs per frame: 872.00 -> 872.01 | No clear effect |
| naive training on UGC360 without FGR | DCVC-HEM · Perspective datasets average | BD-Rate (%): 0.00 -> 7.39 | Hurt |
Closest papers by meaning
- Towards Practical Real-Time Neural Video Compression (CVPR 2025 · similarity 0.90)
- Neural Video Compression with Feature Modulation (CVPR 2024 · similarity 0.90)
- NVRC: Neural Video Representation Compression (NeurIPS 2024 · similarity 0.88)
- Neural Video Compression with Context Modulation (CVPR 2025 · similarity 0.88)
- Augmented Deep Contexts for Spatially Embedded Video Coding (CVPR 2025 · similarity 0.87)
- VRVVC: Variable-Rate NeRF-Based Volumetric Video Compression (AAAI 2025 · 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.
