提出视频深度后处理框架VDPP，实现高速高精度边缘部署。
VDPP: Video Depth Post-Processing for Speed and Scalability
- 将后处理从全场景重建转为低分辨率几何精修，提升效率。
- 在Jetson Orin Nano上达43.5帧以上，保持端到端模型的时序一致性。
- 无需依赖RGB图像，可无缝接入任意新发布的单图深度模型。
视频深度估计在自动驾驶到混合现实等应用中至关重要。现有端到端视频深度模型虽性能领先，但作为紧密耦合系统，当更优单图深度模型发布时存在显著适应延迟。为解决此问题，后处理方法如NVDS提供了无需重训练的模块化替代方案。然而，现有后处理方法仍因速度慢、精度低及依赖RGB图像，难以媲美端到端系统。本文提出VDPP（Video Depth Post-Processing）框架，通过将范式从计算昂贵的场景重建转向目标化的几何精修，在低分辨率空间内仅进行几何优化，实现>43.5 FPS的超高帧率（NVIDIA Jetson Orin Nano），同时保持与端到端系统相当的时序连贯性。采用密集残差学习驱动几何表示，而非完整重建。此外，其完全不依赖RGB的架构确保了真正的可扩展性，可立即集成任何演进中的单图深度模型。实验表明，VDPP在速度、精度与内存效率间取得更优平衡，是实时边缘部署的最佳选择。
原文摘要 · Abstract (English)
Video depth estimation is essential for providing 3D scene structure in applications ranging from autonomous driving to mixed reality. Current end-to-end video depth models have established state-of-the-art performance. Although current end-to-end (E2E) models have achieved state-of-the-art performance, they function as tightly coupled systems that suffer from a significant adaptation lag whenever superior single-image depth estimators are released. To mitigate this issue, post-processing methods such as NVDS offer a modular plug-and-play alternative to incorporate any evolving image depth model without retraining. However, existing post-processing methods still struggle to match the efficiency and practicality of E2E systems due to limited speed, accuracy, and RGB reliance. In this work, we revitalize the role of post-processing by proposing VDPP (Video Depth Post-Processing), a framework that improves the speed and accuracy of post-processing methods for video depth estimation. By shifting the paradigm from computationally expensive scene reconstruction to targeted geometric refinement, VDPP operates purely on geometric refinements in low-resolution space. This design achieves exceptional speed (>43.5 FPS on NVIDIA Jetson Orin Nano) while matching the temporal coherence of E2E systems, with dense residual learning driving geometric representations rather than full reconstructions. Furthermore, our VDPP's RGB-free architecture ensures true scalability, enabling immediate integration with any evolving image depth model. Our results demonstrate that VDPP provides a superior balance of speed, accuracy, and memory efficiency, making it the most practical solution for real-time edge deployment. Our project page is at https://github.com/injun-baek/VDPP
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。