Research map / 3D vision / Depth and stereo
HDR Environment Map Estimation for Real-Time Augmented Reality
Gowri Somanath, Daniel Kurz
Check 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 ProjectionLoss rather than MSE to retrieve environment maps | Environment-map retrieval for rendered-lighting similarity · 380 reference images | intersection with top-5 SSIM retrievals: 1.6±0.7 vs 0.6±0.5 | Improved |
| Rank rendered images using SSIM | Rendered-image similarity judgments · 380 reference images | participant selection rate for a top-10 SSIM image: 95% | Improved |
| Estimate environment maps with EnvMapNet rather than Gardner et al.'s method | EnvMapNet · Real-world test scenes | qualitative lighting and shadow similarity | Improved |
Closest papers by meaning
- Rendering-Aware HDR Environment Map Prediction from a Single Image (AAAI 2022 · similarity 0.92)
- HDR-NeRF: High Dynamic Range Neural Radiance Fields (CVPR 2022 · similarity 0.86)
- DeepLight: Learning Illumination for Unconstrained Mobile Mixed Reality (CVPR 2019 · similarity 0.86)
- Video Generation Models Are Inherent Lighting Estimators (ECCV 2026 · similarity 0.86)
- LuxDiT: Lighting Estimation with Video Diffusion Transformer (NeurIPS 2025 · similarity 0.85)
- High Dynamic Range Novel View Synthesis with Single Exposure (ICML 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.
