AI Paper Atlas

Research map / 3D vision / 3D generation

MAIR: Multi-View Attention Inverse Rendering With 3D Spatially-Varying Lighting Estimation

JunYong Choi, SeokYeong Lee, Haesol Park, Seung-Won Jung, Ig-Jae Kim, Junghyun Cho

CVPR 2023 · 3D vision › 3D generation · approach: Learning 3D reconstruction from images · 10 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 multi-view inverse rendering with MVS depth and confidenceMAIR · OpenRooms FF testAlbedo MSE: 0.569 -> 0.368Improved
Use multi-view inverse rendering with MVS depth and confidenceMAIR · OpenRooms FF testRe-rendering MSE: 0.554 -> 0.633Hurt
Add ContextNet local scene features (ablation)MAIR material estimation · OpenRooms FF testAlbedo MSE: 0.498 -> 0.423Improved
Add RefineNet after pixel-wise MVANet (ablation)MAIR material estimation · OpenRooms FF testAlbedo MSE: 0.661 -> 0.423Improved
Add the specular radiance feature (ablation)MAIR material estimation · OpenRooms FF testRoughness MSE: 3.056 -> 2.739Improved
Use physically motivated microfacet-based specular encoding (ablation)MAIR material estimation · OpenRooms FF testRoughness MSE: 3.085 -> 2.739Improved
Increase incident-light SG lobe count from 1 to 3 (ablation)MAIR direct-light estimation · OpenRooms FFsi-MSE: 0.106 -> 0.101Improved
Increase incident-light SG lobe count from 3 to 6 (ablation)MAIR direct-light estimation · OpenRooms FFGPU Memory: 12.72 -> 14.94 GBHurt
Use depth-projection-based multi-view weights in MVANet (ablation)MAIR material estimation · Increasing number of viewsMaterial estimation accuracyImproved
Remove multi-view weights (ablation)MAIR material estimation · Increasing number of viewsMaterial estimation accuracyNo clear effect
Provide exitant direct-light volume V_DL instead of global lighting feature (ablation)MAIR spatially varying lighting estimation · Indirect lighting estimationConvergenceImproved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

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