Research map / 3D vision / 3D generation
Single-View View Synthesis With Multiplane Images
Check 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 |
|---|---|---|---|
| add scale-invariant synthesis (compared with removing it and sparse depth loss) (ablation) | Single-view MPI · RealEstate10K, n=5 and n=10 | LPIPS_all: 0.149 -> 0.103; 0.221 -> 0.155 | Helped |
| add sparse depth supervision (ablation) | Single-view MPI · RealEstate10K, n=5 and n=10 | LPIPS_all: 0.120 -> 0.103; 0.178 -> 0.155 | Helped |
| add edge-aware disparity smoothness (ablation) | Single-view MPI · RealEstate10K, n=10 | LPIPS_all: 0.159 -> 0.155 | Helped |
| add edge-aware disparity smoothness (ablation) | Single-view MPI · iBims-1 | rel: 0.24 -> 0.21 | Helped |
| add predicted background content (ablation) | Single-view MPI · RealEstate10K, n=10 | LPIPS_all: 0.162 -> 0.155 | Helped |
| add predicted background content (ablation) | Single-view MPI · RealEstate10K, disoccluded pixels, n=5 and n=10 | PSNR_disocc: 18.7 -> 19.7; 17.7 -> 17.9 | Helped |
| add predicted background content (ablation) | Single-view MPI · KITTI city, disoccluded pixels, 384 × 128 and 1240 × 375 | PSNR disocc.: 16.9 -> 17.5; 16.7 -> 17.4 | Helped |
| add predicted background content (ablation) | Single-view MPI · RealEstate10K, n=5 | PSNR_all: 26.8 -> 26.4 | Hurt |
| add predicted background content (ablation) | Single-view MPI · RealEstate10K, n=5 and n=10 | PSNR_all: 26.8 -> 26.4; 23.7 -> 23.5 | Mixed |
Closest papers by meaning
- Novel View Synthesis with Pixel-Space Diffusion Models (CVPR 2025 · similarity 0.90)
- One View Is Enough: In-the-Wild Monocular Pretraining for Novel View Generation (NeurIPS 2026 · similarity 0.89)
- LVSM: A Large View Synthesis Model with Minimal 3D Inductive Bias (ICLR 2025 · similarity 0.89)
- Efficient-3Dim: Learning a Generalizable Single-image Novel-view Synthesizer in One Day (ICLR 2024 · similarity 0.88)
- NAMVIS: Next-Scale Autoregressive Multi-View Image Synthesis (NeurIPS 2026 · similarity 0.87)
- EscherNet: A Generative Model for Scalable View Synthesis (CVPR 2024 · 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.