用单次偏振图像提升单目法向估计，无需重新训练。
Poppy: Polarization-based Plug-and-Play Guidance for Enhancing Monocular Normal Estimation
- 测试时利用单张偏振图优化法向，不改动原有模型。
- 合成数据上误差降低23%-26%，真实数据上降6%-16%。
- 适合处理反光、无纹理、暗色等难样本的场景。
基于大规模RGB-法向数据训练的单目表面法向估计器，在反光、无纹理和暗色表面等边缘情况表现不佳。偏振信息独立于纹理和反照率，可提供物理层面的补充。现有偏振方法需多视角采集或专用训练数据，泛化性受限。本文提出Poppy，一种无需训练的框架，仅通过测试时的单次偏振测量，即可优化任意冻结的RGB骨干模型输出的法向。保持骨干权重不变，Poppy优化每像素的输入RGB与输出法向偏移，并学习反射率分解。可微分渲染层将优化后的法向转换为偏振预测，惩罚与观测信号的差异。在七个基准和三种骨干架构（扩散、流、前馈）上，合成数据上平均角度误差降低23%-26%，真实数据上降低6%-16%。结果表明，测试时引入偏振提示可有效提升复杂表面的法向估计精度，无需重训练。
原文摘要 · Abstract (English)
Monocular surface normal estimators trained on large-scale RGB-normal data often perform poorly in the edge cases of reflective, textureless, and dark surfaces. Polarization encodes surface orientation independently of texture and albedo, offering a physics-based complement for these cases. Existing polarization methods, however, require multi-view capture or specialized training data, limiting generalization. We introduce Poppy, a training-free framework that refines normals from any frozen RGB backbone using single-shot polarization measurements at test time. Keeping backbone weights frozen, Poppy optimizes per-pixel offsets to the input RGB and output normal along with a learned reflectance decomposition. A differentiable rendering layer converts the refined normals into polarization predictions and penalizes mismatches with the observed signal. Across seven benchmarks and three backbone architectures (diffusion, flow, and feed-forward), Poppy reduces mean angular error by 23-26% on synthetic data and 6-16% on real data. These results show that guiding learned RGB-based normal estimators with polarization cues at test time refines normals on challenging surfaces without retraining.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。