Research map / 3D vision / Depth and stereo
Using Unknown Occluders to Recover Hidden Scenes
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 |
|---|---|---|---|
| Estimate the unknown occluder from sparse temporal difference frames, then deconvolve to recover the scene | Passive NLoS imaging · Simulated scene, 25dB SNR | reconstruction quality | Helped |
| Estimate the occluder without prior knowledge of its shape | Passive NLoS imaging · Live-action scene | reconstruction quality | Helped |
| Use an unknown estimated occluder instead of a known pinspeck occluder | Passive NLoS imaging · LCD monitor scene | reconstruction quality | Hurt |
| Recover more complex occluders rather than simpler ones | Unknown-occluder method · Occluder recovery | reconstruction quality | Hurt |
Closest papers by meaning
- Inferring Light Fields From Shadows (CVPR 2018 · similarity 0.88)
- O^2-Recon: Completing 3D Reconstruction of Occluded Objects in the Scene with a Pre-trained 2D Diffusion Model (AAAI 2024 · similarity 0.86)
- Virtual Scanning: Unsupervised Non-line-of-sight Imaging from Irregularly Undersampled Transients (NeurIPS 2024 · similarity 0.85)
- Transient Glimpses: Unveiling Occluded Backgrounds through the Spike Camera (AAAI 2024 · similarity 0.84)
- RobIR: Robust Inverse Rendering for High-Illumination Scenes (NeurIPS 2024 · similarity 0.84)
- Slice3D: Multi-Slice Occlusion-Revealing Single View 3D Reconstruction (CVPR 2024 · similarity 0.83)
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.