Research map / 3D vision / 3D generation
Embedding Novel Views in a Single JPEG Image
Yue Wu, Guotao Meng, Qifeng Chen
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 adversarial (GAN) training (ablation) | MPI embedding model · RealEstate10K, Stereo-Mag MPI embedding image | PSNR: 32.884 -> 34.616 | Mixed |
| add adversarial (GAN) training (ablation) | MPI embedding model · RealEstate10K, Stereo-Mag MPI rendered views | PSNR: 35.174 -> 36.683 | Improved |
| add random render module (ablation) | MPI embedding model · RealEstate10K, Stereo-Mag MPI rendered views | PSNR: 32.301 -> 36.683 | Improved |
| add random render module (ablation) | MPI embedding model · RealEstate10K, Stereo-Mag MPI embedding image | PSNR: 33.998 -> 34.616 | Mixed |
| add frequency-domain loss (ablation) | MPI embedding model · RealEstate10K, Stereo-Mag MPI embedding image | PSNR: 30.911 -> 34.616 | Improved |
| add frequency-domain loss (ablation) | MPI embedding model · RealEstate10K, Stereo-Mag MPI rendered views | PSNR: 38.105 -> 36.683 | Hurt |
| add frequency-domain loss (ablation) | MPI embedding model · RealEstate10K, PB-MPI, embedding image | PSNR: 27.796 -> 36.736 | Improved |
| add render module (ablation) | MPI embedding model · RealEstate10K, PB-MPI, rendered views | PSNR: 27.497 -> 32.840 | Improved |
| use proposed architecture instead of Video Snapshot | Video Snapshot · RealEstate10K, Stereo-Mag MPI rendered views | PSNR: 27.066 -> 36.683 | Improved |
| use embedded MPI instead of single-image view synthesis | S-MPI / SynSin · RealEstate10K, rendered views | PSNR: 24.078 -> 26.732 | Improved |
| use MPI embedding instead of LDI | LDI · Render time vs LDI | render time (s): 42.3 -> 0.017 | Improved |
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.
- SynSin — SynSin: End-to-End View Synthesis From a Single Image (CVPR 2020) · better on 1 of 1 shared result
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
- Novel View Synthesis with Pixel-Space Diffusion Models (CVPR 2025 · similarity 0.82)
- ViewFusion: Towards Multi-View Consistency via Interpolated Denoising (CVPR 2024 · similarity 0.82)
- MultiDiff: Consistent Novel View Synthesis from a Single Image (CVPR 2024 · similarity 0.81)
- Efficient-3Dim: Learning a Generalizable Single-image Novel-view Synthesizer in One Day (ICLR 2024 · similarity 0.81)
- JDEC: JPEG Decoding via Enhanced Continuous Cosine Coefficients (CVPR 2024 · similarity 0.81)
- PICD: Versatile Perceptual Image Compression with Diffusion Rendering (CVPR 2025 · similarity 0.81)
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.
