Rotation Conditional Spherical Neural Fields for Learning a Natural Illumination Prior Supplementary Material
–Neural Information Processing Systems
A.2 Gamma Correction For display, all linear HDR images I had their gamma adjusted using the following process: 1. Adjust exposure to set the white level to the p-th percentile ( p = 98) I I percentile(I, p) 2. Clamp between [0, 1] I clamp(I, 0, 1) 3. Apply gamma correction using the standard sRGB gamma curve: γRGB (I) = null 12 .92 We include additional qualitative results of the RENI model. Figure 3 demonstrates performance differences between RENI and SH at the environment completion task. RENI's prior on natural illumination enables significantly more Figure 7 shows one of RENI's failure cases. 2 Ground Truth Ground Truth 27 108 147 27 108 147 RENI SH SG RENI SH SG RENI SH SG RENI SH SG Heat maps with log-scale colour bars for ground truth and RENI are also shown. Heat maps with log-scale colour bars for ground truth and RENI are also shown.
Neural Information Processing Systems
Aug-17-2025, 11:37:29 GMT
- Country:
- Europe
- Germany (0.05)
- United Kingdom (0.06)
- Europe
- Technology:
- Information Technology > Artificial Intelligence
- Machine Learning (0.31)
- Vision (0.31)
- Information Technology > Artificial Intelligence