Research map / 3D vision / Face and shape
Mirror Illusion Art
Xiaopei Zhu, Zeyuan Li, Jun Zhu, Xiaolin Hu
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 PAC component selection (ablation) | AutoMIA · Mirror-2D (ablation) | Noise Level: 0.248 -> 0.049 | Improved |
| add PAC component selection (ablation) | AutoMIA · Mirror-2D (ablation) | Shape Score: 0.629 -> 0.931 | Improved |
| add PWA background noise suppression (ablation) | AutoMIA · Mirror-2D (ablation) | Noise Level: 0.373 -> 0.049 | Improved |
| add PWA background noise suppression (ablation) | AutoMIA · Mirror-2D (ablation) | Shape Score: 0.790 -> 0.931 | Improved |
| add IVP internal voxel preservation (ablation) | AutoMIA · Mirror-2D (ablation) | Shape Score: 0.748 -> 0.931 | Improved |
| add IVP internal voxel preservation (ablation) | AutoMIA · Mirror-2D (ablation) | Noise Level: 0.050 -> 0.049 | No clear effect |
| add SCD shape-color decoupled optimization (ablation) | AutoMIA · Mirror-2D (ablation) | Shape Score: 0.548 -> 0.931 | Improved |
| add SCD shape-color decoupled optimization (ablation) | AutoMIA · Mirror-2D (ablation) | Smooth Level: 0.755 -> 0.989 | Improved |
| add PAC component selection (ablation) | AutoMIA · Mirror-2D (ablation) | Color Score: 0.323 -> 0.018 | Improved |
| use AutoMIA instead of Shadow Art Revisited | SAR · Mirror-2D | Shape Score: 0.668 -> 0.931 | Improved |
| increase voxel volume from 128 to 256 (ablation) | AutoMIA · Mirror-2D (volume size) | Shape Score: 0.931 -> 0.972; time 76s -> 185s | Mixed |
| increase ray sampling density from 150 to 220 (ablation) | AutoMIA · Mirror-2D (ray sampling) | Shape Score: 0.931 -> 0.684 | Hurt |
Closest papers by meaning
- MirrorVerse: Pushing Diffusion Models to Realistically Reflect the World (CVPR 2025 · similarity 0.84)
- LookingGlass: Generative Anamorphoses via Laplacian Pyramid Warping (CVPR 2025 · similarity 0.83)
- Pygmalion Effect in Vision: Image-to-Clay Translation for Reflective Geometry Reconstruction (NeurIPS 2026 · similarity 0.82)
- MIRROR: Make Your Object-Level Multi-View Generation More Consistent with Training-Free Rectification (ICML 2025 · similarity 0.81)
- Multi-times Monte Carlo Rendering for Inter-reflection Reconstruction (NeurIPS 2024 · similarity 0.81)
- MiraGe: Editable 2D Images using Gaussian Splatting (ICML 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.
