# VDPP: Video Depth Post-Processing for Speed and Scalability Source: [VDPP: Video Depth Post-Processing for Speed and Scalability]() Collection index: [llms.txt]() Data updated: 2026-04-23T05:00:05.534Z Authors: Daewon Yoon, Injun Baek, Sangyu Han, Yearim Kim, Nojun Kwak Published: 2026-04-08T04:33:29.000Z ## Abstract 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 ## Recorded benchmark results A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage. - [Video Depth Estimation on Sintel 384x384 (test)](): Video Depth Estimation; Sintel 384x384 (test); Abs Rel Error: 0.312. - [Video Depth Estimation Latency on Bonn (test)](): Video Depth Estimation; Bonn (test); FPS: 76. - [Monocular Video Depth Estimation on NYU Video v2](): Monocular Video Depth Estimation; NYU Video v2; Absolute Relative Error: 0.132. - [Video Depth Estimation on Sintel](): Video Depth Estimation; Sintel; Delta Threshold Accuracy (1.25): not recorded. - [Video Depth Estimation on Sintel (test)](): Video Depth Estimation; Sintel (test); Delta 1 Accuracy: not recorded. - [Video Depth Estimation on NYUDV2 (test)](): Video Depth Estimation; NYUDv2 (test); delta1: not recorded. ## Original sources and implementation [Original paper]() [PDF]()