Research map / Video / Video segmentation and tracking
HyperReel: High-Fidelity 6-DoF Video With Ray-Conditioned Sampling
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 ray-conditioned sample prediction with HyperReel's volume representation | HyperReel · DoNeRF 800×800 | PSNR: 30.9 -> 35.1 | Helped |
| Use HyperReel instead of Neural 3D Video | Technicolor · Technicolor | PSNR: 31.8 -> 32.7 | Helped |
| Use HyperReel instead of Neural 3D Video | Technicolor · Technicolor | SSIM: 0.958 -> 0.906 | Hurt |
| Use HyperReel instead of NeRFPlayer | Neural 3D Video dataset · Neural 3D Video | PSNR: 30.7 -> 31.1 | Helped |
| Use HyperReel instead of NeRFPlayer | Google LF videos · Google LF videos | PSNR: 25.8 -> 28.8 | Helped |
| Remove the ray-conditioned sample prediction network (ablation) | HyperReel · Technicolor | PSNR: 32.73 -> 29.08 | Hurt |
| Use a Tiny network instead of the full network (ablation) | HyperReel · Technicolor | PSNR: 32.73 -> 30.09 | Hurt |
| Use a Small network instead of the full network (ablation) | HyperReel · Technicolor | PSNR: 32.73 -> 31.76 | Hurt |
| Set keyframes every frame rather than every 4 frames (ablation) | HyperReel · Technicolor | PSNR: 32.73 -> 32.34 | Hurt |
| Set keyframes every 16 frames rather than every 4 frames (ablation) | HyperReel · Technicolor | PSNR: 32.73 -> 32.07 | Hurt |
| Set keyframes every 50 frames rather than every 4 frames (ablation) | HyperReel · Technicolor | PSNR: 32.73 -> 32.35 | Hurt |
| Add point offsets to predicted sample points (ablation) | HyperReel · DoNeRF Forest | PSNR: 34.86 -> 36.34 | Helped |
Closest papers by meaning
- HiCoM: Hierarchical Coherent Motion for Dynamic Streamable Scenes with 3D Gaussian Splatting (NeurIPS 2024 · similarity 0.85)
- HyRF: Hybrid Radiance Fields for Memory-efficient and High-quality Novel View Synthesis (NeurIPS 2025 · similarity 0.85)
- Compressing Streamable Free-Viewpoint Videos to 0.1 MB per Frame (AAAI 2025 · similarity 0.84)
- DaReNeRF: Direction-aware Representation for Dynamic Scenes (CVPR 2024 · similarity 0.84)
- Novel View Synthesis from A Few Glimpses via Test-Time Natural Video Completion (NeurIPS 2025 · similarity 0.84)
- ReCon-GS: Continuum-Preserved Guassian Streaming for Fast and Compact Reconstruction of Dynamic Scenes (NeurIPS 2025 · 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.