Novel View Synthesis
Synthesize a target image with an arbitrary target camera pose from given source images and their camera poses.
See Wiki for more introductions.
The Synthesis method include: NeRF, MPI and so on.
( Image credit: Multi-view to Novel view: Synthesizing novel views with Self-Learned Confidence )
Papers
Showing 1–10 of 1441 papers
All datasetsLLFFMip-NeRF 360NeRFTanks and TemplesRefRefDONeRF: Evaluation DatasetX3DRTMVScanNetACIDSWORDHDR-GS
Benchmark Results
| # | Model | Metric | Claimed | Verified | Status |
|---|---|---|---|---|---|
| 1 | TensoRF + NeRFLiX++ | PSNR | 29.24 | — | Unverified |
| 2 | TensoRF + NeRFLiX | PSNR | 28.94 | — | Unverified |
| 3 | Plenoxels + NeRFLiX | PSNR | 28.61 | — | Unverified |
| 4 | Self-Organizing Gaussians | PSNR | 25.63 | — | Unverified |
| 5 | HAC 3DGS | PSNR | 24.4 | — | Unverified |
| 6 | Compact3D | PSNR | 23.47 | — | Unverified |
| 7 | 3D Gaussian Splatting | PSNR | 23.14 | — | Unverified |
| 8 | Mip-NERF 360 | PSNR | 19.65 | — | Unverified |
| 9 | DIVeR + NeRFLiX | SSIM | 0.92 | — | Unverified |
| 10 | C3DGS | PSNR | 0.23 | — | Unverified |