Research map / Label-efficient and robust learning / Recognition and long-tail
Hierarchical Disentangled Representation Learning for Outdoor Illumination Estimation and Editing
Piaopiao Yu, Jie Guo, Fan Huang, Cheng Zhou, Hongwei Che, Xiao Ling, Yanwen Guo
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 |
|---|---|---|---|
| add information-theory loss L_info (ablation) | HDSky AE1 · Sunny/50 panoramas | RMSE: 0.785 -> 0.569 | Improved |
| add sun loss L_sun (ablation) | HDSky AE1 · Sunny/50 panoramas | RMSE: 0.757 -> 0.569 | Improved |
| add sun position map P_pos (ablation) | HDSky AE1 · Sunny/50 panoramas | RMSE: 0.774 -> 0.569 | Improved |
| add information-theory loss L_info (ablation) | HDSky AE1 · Sunny/50 renders | RMSE: 0.028 -> 0.025 | Improved |
| add sun loss L_sun (ablation) | HDSky AE1 · Sunny/50 renders | RMSE: 0.033 -> 0.025 | Improved |
| add sun position map P_pos (ablation) | HDSky AE1 · Sunny/50 renders | RMSE: 0.026 -> 0.025 | Improved |
| use sky:sun latent dimension ratio 8:53 instead of 16:45 (ablation) | HDSky predictor · Sunny images (300) | RMSE: 11.84 -> 10.28 | Improved |
| use ratio 8:53 instead of 24:37 (ablation) | HDSky predictor · Sunny images (300) | RMSE: 12.31 -> 10.28 | Improved |
| use ratio 8:53 instead of 32:29 (ablation) | HDSky predictor · Sunny images (300) | RMSE: 14.18 -> 10.28 | Improved |
| use ratio 8:53 instead of 48:13 (ablation) | HDSky predictor · Sunny images (300) | RMSE: 10.51 -> 10.28 | Improved |
| disentangled sky/sun representation instead of single latent vector (SkyNet) | HDSky reconstruction · Sunny/50 panoramas | RMSE: 1.532 -> 0.569 | Improved |
| disentangled representation instead of SkyNet single vector | HDSky predictor · Cloudy/100 renders | RMSE: 0.101 -> 0.030 | Improved |
Closest papers by meaning
- Estimating Spatially-Varying Lighting in Urban Scenes with Disentangled Representation (ECCV 2022 · similarity 0.90)
- Deep Sky Modeling for Single Image Outdoor Lighting Estimation (CVPR 2019 · similarity 0.90)
- Deep Outdoor Illumination Estimation (CVPR 2017 · similarity 0.89)
- All-Weather Deep Outdoor Lighting Estimation (CVPR 2019 · similarity 0.89)
- Spatially-Varying Outdoor Lighting Estimation From Intrinsics (CVPR 2021 · similarity 0.88)
- Rethinking Nighttime Image Deraining via Learnable Color Space Transformation (NeurIPS 2025 · similarity 0.84)
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.
