Research map / 3D vision / Depth and stereo
3D Moments From Near-Duplicate Photos
Check your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (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 feature LDIs with scene-flow-based rendering rather than the tested baseline pipelines | 3D Moments · NVIDIA Dynamic Scene | LPIPS: 0.177 -> 0.145 | Helped |
| Use feature LDIs with scene-flow-based rendering rather than the tested baseline pipelines | 3D Moments · UCSD Multi-View Video | LPIPS: 0.120 -> 0.078 | Helped |
| Add learned features instead of splatting RGB colors (ablation) | 3D Moments · NVIDIA Dynamic Scene | PSNR: 21.16 -> 21.72 | Helped |
| Add learned features instead of splatting RGB colors (ablation) | 3D Moments · NVIDIA Dynamic Scene | LPIPS: 0.173 -> 0.145 | Helped |
| Add color and depth inpainting to the LDIs (ablation) | 3D Moments · NVIDIA Dynamic Scene | SSIM: 0.685 -> 0.702 | Helped |
| Add color and depth inpainting to the LDIs (ablation) | 3D Moments · NVIDIA Dynamic Scene | LPIPS: 0.145 -> 0.145 | No clear effect |
| Use bidirectional instead of single-directional scene flow (ablation) | 3D Moments · NVIDIA Dynamic Scene | LPIPS: 0.151 -> 0.145 | Helped |
| Use bidirectional instead of single-directional scene flow (ablation) | 3D Moments · NVIDIA Dynamic Scene | PSNR: 21.56 -> 21.72 | Helped |
Closest papers by meaning
- Layered Motion Fusion: Lifting Motion Segmentation to 3D in Egocentric Videos (CVPR 2025 · similarity 0.84)
- Scene Splatter: Momentum 3D Scene Generation from Single Image with Video Diffusion Model (CVPR 2025 · similarity 0.84)
- World from Motion: Generative Dynamic Gaussian Reconstruction from Monocular Video (NeurIPS 2026 · similarity 0.84)
- Generating 3D-Consistent Videos from Unposed Internet Photos (CVPR 2025 · similarity 0.84)
- MoDGS: Dynamic Gaussian Splatting from Casually-captured Monocular Videos with Depth Priors (ICLR 2025 · similarity 0.84)
- Optimizing 4D Gaussians for Dynamic Scene Video from Single Landscape Images (ICLR 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.