Trajectory Densification and Depth from Perspective-based Blur

TL;DR

This paper introduces a novel method to estimate depth from perspective-based blur in videos by analyzing optical trajectories and employing a joint optical design, achieving accurate depth maps without mechanical stabilizers.

Contribution

It presents a new approach combining optical design and vision models to densify sparse trajectories and estimate depth from motion blur in videos.

Findings

Strong performance over large depth ranges

High accuracy in dense depth reconstruction

Superior precision in handheld shooting scenarios

Abstract

In the absence of a mechanical stabilizer, the camera undergoes inevitable rotational dynamics during capturing, which induces perspective-based blur especially under long-exposure scenarios. From an optical standpoint, perspective-based blur is depth-position-dependent: objects residing at distinct spatial locations incur different blur levels even under the same imaging settings. Inspired by this, we propose a novel method that estimate metric depth by examining the blur pattern of a video stream and dense trajectory via joint optical design algorithm. Specifically, we employ off-the-shelf vision encoder and point tracker to extract video information. Then, we estimate depth map via windowed embedding and multi-window aggregation, and densify the sparse trajectory from the optical algorithm using a vision-language model. Evaluations on multiple depth datasets demonstrate that our method attains strong performance over large depth range, while maintaining favorable generalization. Relative to the real trajectory in handheld shooting settings, our optical algorithm achieves superior precision and the dense reconstruction maintains strong accuracy.