用信心引导的扩散模型，让深度传感器在噪声下仍能保持精准和连贯。
Towards Robust Time-of-Flight Depth Denoising with Confidence-Aware Diffusion Model
- 基于预训练扩散模型，结合信心引导控制去噪过程。
- 在真实数据上实现最优去噪效果，抗噪声能力显著提升。
- 适合需要高精度深度图的机器人、AR/VR等应用。
飞行时间（ToF）传感器可高效获取场景深度，但非线性深度构建常导致噪声方差极大甚至出现无效区域。现有基于深度神经网络的方法虽提升了去噪精度，但在严重噪声干扰下表现不佳，因缺乏对ToF数据分布的充分先验知识。本文提出DepthCAD，一种新型ToF去噪方法：利用Stable Diffusion中的丰富先验知识保证全局结构平滑，同时通过信心引导机制维持局部度量准确性。为适配预训练图像扩散模型，我们在转换为深度图前对原始ToF相关测量值进行动态范围归一化处理并施加扩散。实验验证了该方案达到当前最优性能，真实数据评估进一步证明其对实际ToF噪声的鲁棒性。
原文摘要 · Abstract (English)
Time-of-Flight (ToF) sensors efficiently capture scene depth, but the nonlinear depth construction procedure often results in extremely large noise variance or even invalid areas. Recent methods based on deep neural networks (DNNs) achieve enhanced ToF denoising accuracy but tend to struggle when presented with severe noise corruption due to limited prior knowledge of ToF data distribution. In this paper, we propose DepthCAD, a novel ToF denoising approach that ensures global structural smoothness by leveraging the rich prior knowledge in Stable Diffusion and maintains local metric accuracy by steering the diffusion process with confidence guidance. To adopt the pretrained image diffusion model to ToF depth denoising, we apply the diffusion on raw ToF correlation measurements with dynamic range normalization before converting to depth maps. Experimental results validate the state-of-the-art performance of the proposed scheme, and the evaluation on real data further verifies its robustness against real-world ToF noise.
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。