Research map / 3D vision / 3D generation
EYE3:Turn Anything into Naked-eye 3D
Yingde Song, Zongyuan Yang, Baolin Liu, Yongping Xiong, Sai Chen, Lan Yi, Zhaohe Zhang, Xunbo Yu
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 mask-guided fine-tuned video inpainting (ablation) | EYE3 · Blender indoor | PSNR: 22.1539 -> 22.3988 | Improved |
| add mask-guided fine-tuned video inpainting (ablation) | EYE3 · Blender outdoor | PSNR: 18.7026 -> 20.3076 | Improved |
| add mask-guided fine-tuned video inpainting (ablation) | EYE3 · Blender outdoor | SSIM: 0.4892 -> 0.5407 | Improved |
| add mask guidance to the inpainting model (vs unguided) (ablation) | EYE3 · Blender indoor | PSNR: 20.7986 -> 22.3988 | Improved |
| inpaint with a model lacking mask guidance (vs no inpainting) (ablation) | EYE3 · Blender outdoor | PSNR: 18.7026 -> 17.8287 | Hurt |
| use Depth Anything V2 instead of MiDaS V3.1 (ablation) | EYE3 · Blender outdoor | PSNR: 18.7840 -> 20.3076 | Improved |
| use Depth Anything V2 instead of Depth Pro (ablation) | EYE3 · Blender outdoor | PSNR: 18.5279 -> 20.3076 | Improved |
| use Depth Anything V2 instead of DepthAnything (ablation) | EYE3 · Blender outdoor | PSNR: 19.2035 -> 20.3076 | Improved |
| use Depth Anything V2 instead of MiDaS V3.1 (ablation) | EYE3 · Blender indoor | PSNR: 22.2424 -> 22.3988 | No clear effect |
| use Depth Anything V2 instead of DepthAnything (ablation) | EYE3 · Blender indoor | SSIM: 0.6797 -> 0.7335 | Improved |
Closest papers by meaning
- TeTriRF: Temporal Tri-Plane Radiance Fields for Efficient Free-Viewpoint Video (CVPR 2024 · similarity 0.85)
- HyRF: Hybrid Radiance Fields for Memory-efficient and High-quality Novel View Synthesis (NeurIPS 2025 · similarity 0.85)
- IllumiNeRF: 3D Relighting Without Inverse Rendering (NeurIPS 2024 · similarity 0.85)
- ProbeSDF: Light Field Probes For Neural Surface Reconstruction (CVPR 2025 · similarity 0.85)
- S2D-LFE: Sparse-to-Dense Light Field Event Generation (CVPR 2025 · similarity 0.84)
- Structured 3D Latents for Scalable and Versatile 3D Generation (CVPR 2025 · similarity 0.84)
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.
