Research map / 3D vision / 3D generation
Reflection-aware generative novel view synthesis
GeonU Kim, Shin Dong-Yeon, Tae-Hyun Oh
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 Ref-GeNVS reflection-aware generation | MVGenMaster · Synthetic sparse-input, full scene | PSNR: 16.90 -> 17.95 | Improved |
| add Ref-GeNVS reflection-aware generation | SEVA · Synthetic sparse-input, full scene | PSNR: 13.65 -> 15.51 | Improved |
| add Ref-GeNVS | MVGenMaster · Synthetic sparse-input, reflected region | PSNR: 16.51 -> 18.40 | Improved |
| add Ref-GeNVS | SEVA · Synthetic sparse-input, reflected region | PSNR: 13.31 -> 16.11 | Improved |
| add Ref-GeNVS | MVGenMaster · Synthetic sparse-input, mirror surface | PSNR: 19.41 -> 19.69 | Improved |
| add Ref-GeNVS | SEVA · Synthetic sparse-input, mirror surface | PSNR: 15.25 -> 16.16 | Improved |
| use mirror-masked surface-point plane estimation instead of edge-based estimation (ablation) | Ref-GeNVS · Synthetic data with corrupted mirror masks | DreamSim, LPIPS, CLIP, PSNR | Improved |
| add Ref-GeNVS two-stage pipeline (extra preprocessing and generation) | SEVA · Sparse-view NVS | inference time: 130 -> 397 | Hurt |
Closest papers by meaning
- MirrorVerse: Pushing Diffusion Models to Realistically Reflect the World (CVPR 2025 · similarity 0.91)
- MIRROR: Make Your Object-Level Multi-View Generation More Consistent with Training-Free Rectification (ICML 2025 · similarity 0.90)
- Novel View Synthesis with Pixel-Space Diffusion Models (CVPR 2025 · similarity 0.89)
- NVComposer: Boosting Generative Novel View Synthesis with Multiple Sparse and Unposed Images (CVPR 2025 · similarity 0.87)
- MVGenMaster: Scaling Multi-View Generation from Any Image via 3D Priors Enhanced Diffusion Model (CVPR 2025 · similarity 0.86)
- Efficient-3Dim: Learning a Generalizable Single-image Novel-view Synthesizer in One Day (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.
