Research map / 3D vision / Depth and stereo
Pushing the Boundaries of View Extrapolation 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 |
|---|---|---|---|
| Increase disparity sampling frequency using a 3D CNN and randomized-resolution training | MPI prediction · YouTube Real Estate 10K test triplets | SSIM_fov: 0.838 -> 0.858 | Helped |
| Add the flow-based hidden-content appearance constraint (ablation) | Our MPI prediction pipeline · YouTube Real Estate 10K test triplets | SSIM_occ: 0.811 -> 0.814 | Helped |
| Add the flow-based hidden-content appearance constraint (ablation) | Our MPI prediction pipeline · YouTube Real Estate 10K test triplets | NAT_occ: 0.904 -> 0.931 | Helped |
| Replace the flow-based appearance constraint with directly predicted RGBα planes and an adversarial loss | Our r_init · YouTube Real Estate 10K test triplets | SSIM_occ: 0.811 -> 0.791 | Hurt |
| Replace the flow-based appearance constraint with directly predicted RGBα planes and an adversarial loss | Our r_init · YouTube Real Estate 10K test triplets | NAT_occ: 0.805 -> 0.849 | Helped |
| Inpaint disoccluded pixels separately in each rendered image | Our final MPI renderings · YouTube Real Estate 10K test triplets | SSIM_occ: 0.814 -> 0.691 | Hurt |
| Inpaint disoccluded pixels separately in each rendered image | Our final MPI renderings · YouTube Real Estate 10K test triplets | NAT_occ: 0.931 -> 0.227 | Hurt |
Closest papers by meaning
- GenRec: Knowing Where to Reconstruct and Where to Generate (NeurIPS 2026 · similarity 0.88)
- ExtraNeRF: Visibility-Aware View Extrapolation of Neural Radiance Fields with Diffusion Models (CVPR 2024 · similarity 0.88)
- MultiDiff: Consistent Novel View Synthesis from a Single Image (CVPR 2024 · similarity 0.87)
- NAMVIS: Next-Scale Autoregressive Multi-View Image Synthesis (NeurIPS 2026 · similarity 0.86)
- MACRO: Training-free Multi-plane Attention for Closeup Render Optimization (NeurIPS 2026 · similarity 0.86)
- UMAMI: Unifying Masked Autoregressive Models and Deterministic Rendering for View Synthesis (NeurIPS 2025 · similarity 0.86)
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.