T-SBI 光照先验研究：对换脸检测的帮助有限
Does an Illumination Prior Help Face-Swap Detection? A Controlled Study of Temporal Self-Blended Images
这篇论文用三种子对照实验证明 T-SBI 的光照线索并不提升换脸检测，还会让固定阈值比较失真，做深伪检测的人应该看看阈值那部分。
一篇 arXiv 论文研究了 Temporal Self-Blended Images（T-SBI）中光照不一致性能否提升换脸检测。作者用 5 种训练方案、3 个随机种子对比高低 ΔL 训练，AUC 差异都在种子波动范围内。对 506,328 个按属性分桶的样本分析显示，恶劣光照下错误率没有额外下降。但 T-SBI 会移动预测分数分布，在 FaceForensics++ 和 Celeb-DF 上最优阈值分别变化约 0.34 和 0.30；另外在 DFDC 的重度 JPEG 压缩场景下 AUC 从 0.696 提升到 0.780。
Does an Illumination Prior Help Face-Swap Detection? A Controlled Study of Temporal Self-Blended Images
Self-blended images are widely used to train face-swap detectors, but primarily capture blending artifacts. We investigate whether adding illumination inconsistencies improves detection. Temporal Self-Blended Images (T-SBI) transfer lighting statistics between frames of the same video, with the mismatch controlled by luminance difference (ΔL). Using five training regimes and a three-seed comparison of high- and low-ΔL training, we find no evidence of illumination-specific improvements. AUC differences remain within seed variability across four datasets, and an analysis of 506,328 attribute-binned samples shows no preferential reduction in errors under harsh lighting. Instead, T-SBI shifts prediction scores, changing optimal thresholds by approximately 0.34 on FaceForensics++ and 0.30 on Celeb-DF, making comparisons at a fixed threshold misleading. However, T-SBI improves robustness to heavy JPEG compression on DFDC (AUC 0.780 versus 0.696), potentially reflecting greater reliance on low-frequency cues. These findings highlight the importance of evaluating training methods against their intended targets and accounting for threshold effects.
