Research map / 3D vision / Depth and stereo
Motion-From-Blur: 3D Shape and Motion Estimation of Motion-Blurred Objects in Videos
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 |
|---|---|---|---|
| Optimize a shared 3D shape and motion across multiple blurred frames instead of reconstructing each frame independently | MfB versus SfB · Falling Objects | TIoU: 0.701 -> 0.772 | Helped |
| Optimize a shared 3D shape and motion across multiple blurred frames instead of reconstructing each frame independently | MfB versus SfB · Falling Objects | PSNR: 27.18 -> 27.54 | Helped |
| Optimize a shared 3D shape and motion across multiple blurred frames instead of reconstructing each frame independently | MfB versus SfB · TbD-3D | PSNR: 26.54 -> 26.57 | Helped |
| Optimize a shared 3D shape and motion across multiple blurred frames instead of reconstructing each frame independently | MfB versus SfB · TbD | PSNR: 25.66 -> 26.63 | Helped |
| Optimize motion across multiple frames | MfB versus SfB · Synthetic 3D, rotation < 90° | Translation error: 37.8 % -> 20.0 % | Helped |
| Optimize motion across multiple frames | MfB versus SfB · Synthetic 3D, rotation < 90° | Rotation error: 10.9$^{\circ}$ -> 6.4$^{\circ}$ | Helped |
| Optimize motion across multiple frames | MfB versus SfB · Synthetic 3D, rotation < 30° | Translation error: 12.8 % -> 8.8 % | Helped |
| Model abrupt trajectory changes with a bounce | MfB versus SfB · TbD-3D bounce frames (bnc ± 0) | PSNR: 20.77 -> 24.57 | Helped |
| Use multi-frame estimation around a bounce | MfB versus SfB · TbD-3D frames immediately before and after bounces (bnc ± 1) | PSNR: 21.77 -> 25.01 | Helped |
Closest papers by meaning
- BLURD: Benchmarking and Learning using a Unified Rendering and Diffusion Model (NeurIPS 2024 · similarity 0.86)
- World from Motion: Generative Dynamic Gaussian Reconstruction from Monocular Video (NeurIPS 2026 · similarity 0.86)
- BARD-GS: Blur-Aware Reconstruction of Dynamic Scenes via Gaussian Splatting (CVPR 2025 · similarity 0.86)
- Dynamic Gaussian Splatting from Defocused and Motion-blurred Monocular Videos (NeurIPS 2025 · similarity 0.86)
- DynaMoDe-NeRF: Motion-aware Deblurring Neural Radiance Field for Dynamic Scenes (CVPR 2025 · similarity 0.86)
- HiCoM: Hierarchical Coherent Motion for Dynamic Streamable Scenes with 3D Gaussian Splatting (NeurIPS 2024 · similarity 0.86)
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.