Research map / Video / Video segmentation and tracking
Turning Corners Into Cameras: Principles and Methods
Katherine L. Bouman, Vickie Ye, Adam B. Yedidia, Fredo Durand, Gregory W. Wornell, Antonio Torralba, William T. Freeman
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 a less noisy camera (uncompressed Point Grey instead of compressed iPhone 5s video) (ablation) | Edge camera reconstruction · Indoor carpet scene, single-frame reconstruction | sensor noise lambda / reconstruction quality: 5.2 -> 0.8 | Improved |
| use Sony Alpha 7s instead of iPhone 5s (ablation) | Edge camera reconstruction · Indoor carpet scene | sensor noise lambda: 5.2 -> 2.3 | Improved |
| increase distance of hidden person from the corner (ablation) | Single edge camera · Person walking from 2 to 16 feet | signal strength | Hurt |
| add rain or wet ground to outdoor scene (ablation) | Edge camera reconstruction · Outdoor scene, varied weather | trajectory visibility | No clear effect |
| add a second adjacent wall edge (stereo) to triangulate 2-D position | Edge camera · Doorway, natural environment | 2-D localization error | Mixed |
| add temporal smoothness constraint (ablation) | Edge camera MAP estimate · 1-D video reconstruction | regularization vs temporal blur | Mixed |
Closest papers by meaning
- Moving Indoor: Unsupervised Video Depth Learning in Challenging Environments (ICCV 2019 · similarity 0.84)
- What You Can Learn by Staring at a Blank Wall (ICCV 2021 · similarity 0.84)
- 3D Cinemagraphy From a Single Image (CVPR 2023 · similarity 0.84)
- Seurat: From Moving Points to Depth (CVPR 2025 · similarity 0.84)
- Event-Based Stereo Depth Estimation: A Survey (TPAMI 2025 · similarity 0.84)
- Layered Motion Fusion: Lifting Motion Segmentation to 3D in Egocentric Videos (CVPR 2025 · similarity 0.82)
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.
