Research map / 3D vision / 3D generation
DeepStereo: Learning to Predict New Views From the World's Imagery
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 lower-resolution views of larger surrounding areas as multi-resolution context (ablation) | DeepStereo · View synthesis patches | visual quality | Helped |
| Train end-to-end to predict target pixels directly from posed input imagery | DeepStereo · Street View view interpolation | visual quality | Helped |
| Apply DeepStereo to handheld DSLR imagery despite training on different imagery | DeepStereo · Chaurasia et al. imagery | visual quality | Helped |
| Violate the maximum camera motion assumption | DeepStereo · View interpolation with excessive camera motion | visual quality | Hurt |
Closest papers by meaning
- Novel View Synthesis with Pixel-Space Diffusion Models (CVPR 2025 · similarity 0.89)
- Single-View View Synthesis With Multiplane Images (CVPR 2020 · similarity 0.88)
- DeepMVS: Learning Multi-View Stereopsis (CVPR 2018 · similarity 0.88)
- LaVin-DiT: Large Vision Diffusion Transformer (CVPR 2025 · similarity 0.86)
- LVSM: A Large View Synthesis Model with Minimal 3D Inductive Bias (ICLR 2025 · similarity 0.86)
- Win-Win: Training High-Resolution Vision Transformers from Two Windows (ICLR 2024 · 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.