Research map / 3D vision / 3D generation
SLIDE: Single Image 3D Photography With Soft Layering and Depth-Aware Inpainting
Varun Jampani, Huiwen Chang, Kyle Sargent, Abhishek Kar, Richard Tucker, Michael Krainin, Dominik Kaeser, William T. Freeman, David Salesin, Brian Curless, Ce Liu
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 |
|---|---|---|---|
| replace hard-layer 3D-Photo with SLIDE soft layering and depth-aware inpainting | SLIDE · RealEstate10K (t=5) | LPIPS: 0.09 -> 0.06 | Improved |
| replace 3D-Photo with SLIDE | SLIDE · RealEstate10K (t=10) | LPIPS: 0.12 -> 0.10 | Improved |
| replace 3D-Photo with SLIDE | SLIDE · RealEstate10K (t=10) | PSNR: 23.7 -> 23.7 | No clear effect |
| replace 3D-Photo with SLIDE | SLIDE · Dual-Pixels | PSNR: 16.3 -> 16.8 | Improved |
| replace 3D-Photo with SLIDE | SLIDE · Dual-Pixels | LPIPS: 0.27 -> 0.23 | Improved |
| replace 3D-Photo with SLIDE | SLIDE · Mannequin Challenge | PSNR: 18.8 -> 20.0 | Improved |
| replace 3D-Photo with SLIDE | SLIDE · Mannequin Challenge | SSIM: 0.60 -> 0.66 | Improved |
| replace 3D-Photo with SLIDE | SLIDE · Mannequin Challenge | LPIPS: 0.22 -> 0.18 | Improved |
| add end-to-end fine-tuning of depth and inpainting networks (ablation) | SLIDE · RealEstate10K (t=10) | LPIPS: 0.10 -> 0.09 | Improved |
| add end-to-end fine-tuning of depth and inpainting networks (ablation) | SLIDE · RealEstate10K (t=10) | PSNR: 23.7 -> 23.8 | Improved |
| add foreground alpha matting to SLIDE (ablation) | SLIDE · RE10K, Dual-Pixels, Mannequin Challenge | LPIPS/PSNR/SSIM | No clear effect |
| add alpha matting to SLIDE (ablation) | SLIDE · Unsplash user study Set-2 (thin hair) | user preference over 3D-Photo | Improved |
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.
- SynSin — SynSin: End-to-End View Synthesis From a Single Image (CVPR 2020) · better on 5 of 5 shared results
Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.
Closest papers by meaning
- 3D Photography Using Context-Aware Layered Depth Inpainting (CVPR 2020 · similarity 0.87)
- DiGA3D: Coarse-to-Fine Diffusional Propagation of Geometry and Appearance for Versatile 3D Inpainting (ICCV 2025 · similarity 0.85)
- Cue3D: Quantifying the Role of Image Cues in Single-Image 3D Generation (NeurIPS 2025 · similarity 0.84)
- MonoSplat: Generalizable 3D Gaussian Splatting from Monocular Depth Foundation Models (CVPR 2025 · similarity 0.84)
- Track, Inpaint, Resplat: Subject-driven 3D and 4D Generation with Progressive Texture Infilling (NeurIPS 2025 · similarity 0.84)
- $\alpha$Depth: Learning Single-Pass Soft Boundary Decomposition for Stereo Conversion (NeurIPS 2026 · 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.
