AI Paper Atlas

Research map / 3D vision / NeRF and radiance fields

Complementary Intrinsics From Neural Radiance Fields and CNNs for Outdoor Scene Relighting

Siqi Yang, Xuanning Cui, Yongjie Zhu, Jiajun Tang, Si Li, Zhaofei Yu, Boxin Shi

CVPR 2023 · 3D vision › NeRF and radiance fields · approach: Sparse-input NeRF regularization · 8 citations (OpenAlex)

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 changedWhereMeasuredEffect
Use NeRF-produced intrinsic pseudo-labels to train the single-image CNNOutdoor scene intrinsic decomposition · Outdoor landmark image collections, test setPSNR: 23.4755 -> 24.2387Improved
Use NeRF-produced intrinsic pseudo-labels to train the single-image CNNOutdoor scene intrinsic decomposition · Outdoor landmark image collections, test setMSE: 0.0051 -> 0.0038Improved
Use NeRF-produced intrinsic pseudo-labels to train the single-image CNNOutdoor scene intrinsic decomposition · Outdoor landmark image collections, test setSSIM: 0.8595 -> 0.8558Hurt
Use NeRF-produced intrinsic pseudo-labels to train the single-image CNNOutdoor scene intrinsic decomposition · Outdoor landmark image collections, test setLPIPS: 0.1336 -> 0.1354Hurt
Use NeRF-produced intrinsic pseudo-labels to train the single-image CNNOutdoor scene intrinsic decomposition · Outdoor landmark image collections, test setMAE: 0.0543 -> 0.0430Improved
Use NeRF-produced intrinsic pseudo-labels to train the single-image CNNOutdoor scene intrinsic decomposition · Outdoor landmark image collections, test setPSNR: 17.3381 -> 24.2387Improved
Use NeRF-produced intrinsic pseudo-labels to train the single-image CNNOutdoor scene intrinsic decomposition · Outdoor landmark image collections, test setSSIM: 0.5999 -> 0.8558Improved
Use NeRF-produced intrinsic pseudo-labels to train the single-image CNNOutdoor scene intrinsic decomposition · Outdoor landmark image collections, test setMSE: 0.0204 -> 0.0038Improved
Use NeRF-produced intrinsic pseudo-labels to train the single-image CNNOutdoor scene intrinsic decomposition · Outdoor landmark image collections, test setMAE: 0.1176 -> 0.0430Improved
Use NeRF-produced intrinsic pseudo-labels to train the single-image CNNOutdoor scene intrinsic decomposition · Outdoor landmark image collections, test setLPIPS: 0.1512 -> 0.1354Improved
Separate sky rendering from opaque-object photometric rendering using SkyMLP (ablation)Outdoor scene relighting · Outdoor landmark scenesVisual sky realismImproved
Use the hybrid object-sky image formation and combine it with the uninterpretable NeRF-W rendering (ablation)NeRF intrinsic estimation · Outdoor landmark scenesShadow and geometry qualityImproved

Closest papers by meaning

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.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy