Research map / 3D vision / Depth and stereo
3D Cinemagraphy From a Single Image
Xingyi Li, Zhiguo Cao, Huiqiang Sun, Jianming Zhang, Ke Xian, Guosheng Lin
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 |
|---|---|---|---|
| Use the joint 3D animation and novel-view synthesis framework instead of the strongest baseline | 3D Cinemagraphy · Holynski et al. validation set | PSNR: 22.47 -> 23.33 | Improved |
| Use the joint 3D animation and novel-view synthesis framework instead of the strongest baseline | 3D Cinemagraphy · Holynski et al. validation set | SSIM: 0.718 -> 0.776 | Improved |
| Use the joint 3D animation and novel-view synthesis framework instead of the strongest baseline | 3D Cinemagraphy · Holynski et al. validation set | LPIPS: 0.261 -> 0.197 | Improved |
| Add learned feature representation instead of using RGB colors (ablation) | 3D Cinemagraphy · Holynski et al. validation set | PSNR: 21.50 -> 23.33 | Improved |
| Add learned feature representation instead of using RGB colors (ablation) | 3D Cinemagraphy · Holynski et al. validation set | SSIM: 0.674 -> 0.776 | Improved |
| Add learned feature representation instead of using RGB colors (ablation) | 3D Cinemagraphy · Holynski et al. validation set | LPIPS: 0.228 -> 0.197 | Improved |
| Add inpainting when constructing 3D geometry (ablation) | 3D Cinemagraphy · Holynski et al. validation set | PSNR: 22.86 -> 23.33 | Improved |
| Add inpainting when constructing 3D geometry (ablation) | 3D Cinemagraphy · Holynski et al. validation set | SSIM: 0.763 -> 0.776 | Improved |
| Add inpainting when constructing 3D geometry (ablation) | 3D Cinemagraphy · Holynski et al. validation set | LPIPS: 0.216 -> 0.197 | Improved |
| Add bidirectional point-cloud displacement using 3D symmetric animation (ablation) | 3D Cinemagraphy · Holynski et al. validation set | PSNR: 22.99 -> 23.33 | Improved |
| Add bidirectional point-cloud displacement using 3D symmetric animation (ablation) | 3D Cinemagraphy · Holynski et al. validation set | SSIM: 0.768 -> 0.776 | Improved |
| Add bidirectional point-cloud displacement using 3D symmetric animation (ablation) | 3D Cinemagraphy · Holynski et al. validation set | LPIPS: 0.199 -> 0.197 | Improved |
Closest papers by meaning
- Wonderland: Navigating 3D Scenes from a Single Image (CVPR 2025 · similarity 0.86)
- Optimizing 4D Gaussians for Dynamic Scene Video from Single Landscape Images (ICLR 2025 · similarity 0.85)
- DreamScene4D: Dynamic Multi-Object Scene Generation from Monocular Videos (NeurIPS 2024 · similarity 0.85)
- Animate3D: Animating Any 3D Model with Multi-view Video Diffusion (NeurIPS 2024 · similarity 0.85)
- Director3D: Real-world Camera Trajectory and 3D Scene Generation from Text (NeurIPS 2024 · similarity 0.85)
- ViVid-1-to-3: Novel View Synthesis with Video Diffusion Models (CVPR 2024 · similarity 0.85)
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.
