轻量化模型+去噪机制，实现快速高分辨率深度估计
PatchRefiner V2: Fast and Lightweight Real-Domain High-Resolution Metric Depth Estimation
- 用轻量编码器替代重型重构模型，降低计算开销
- 在UnrealStereo4K上精度超越现有方法，推理更快
- 适合实时应用，尤其对真实场景深度感知有提升
现有高分辨率深度估计方法虽性能优异，但常因依赖重型模型和多步推理导致计算效率低下。为此，我们提出PatchRefiner V2（PRV2），以轻量编码器替代重型重构模块，减少模型规模与推理时间，但引入噪声特征。为解决此问题，提出粗到细（C2F）模块及引导去噪单元，用于优化重构特征；同时采用噪声预训练策略，充分挖掘轻量分支潜力。此外，引入尺度-平移不变梯度匹配（SSIGM）损失，增强从合成域到真实域的迁移能力。PRV2在UnrealStereo4K上兼具更高精度与更快速度，参数更少；在CityScape、ScanNet++和KITTI等真实数据集上，深度边界分割更清晰，展现跨域泛化能力。
原文摘要 · Abstract (English)
While current high-resolution depth estimation methods achieve strong results, they often suffer from computational inefficiencies due to reliance on heavyweight models and multiple inference steps, increasing inference time. To address this, we introduce PatchRefiner V2 (PRV2), which replaces heavy refiner models with lightweight encoders. This reduces model size and inference time but introduces noisy features. To overcome this, we propose a Coarse-to-Fine (C2F) module with a Guided Denoising Unit for refining and denoising the refiner features and a Noisy Pretraining strategy to pretrain the refiner branch to fully exploit the potential of the lightweight refiner branch. Additionally, we introduce a Scale-and-Shift Invariant Gradient Matching (SSIGM) loss to enhance synthetic-to-real domain transfer. PRV2 outperforms state-of-the-art depth estimation methods on UnrealStereo4K in both accuracy and speed, using fewer parameters and faster inference. It also shows improved depth boundary delineation on real-world datasets like CityScape, ScanNet++, and KITTI, demonstrating its versatility across domains.
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。