Video Depth without Video Models

TL;DR

RollingDepth transforms a single-image latent diffusion model into a highly effective video depth estimation tool, producing consistent, accurate depth videos for long sequences by combining multi-frame depth estimation with an optimization-based registration.

Contribution

The paper introduces RollingDepth, a novel method that leverages a single-image latent diffusion model for state-of-the-art video depth estimation, addressing temporal consistency and long video processing.

Findings

Outperforms existing video depth estimators in accuracy.

Handles long videos with hundreds of frames efficiently.

Produces temporally consistent depth videos without flickering.

Abstract

Video depth estimation lifts monocular video clips to 3D by inferring dense depth at every frame. Recent advances in single-image depth estimation, brought about by the rise of large foundation models and the use of synthetic training data, have fueled a renewed interest in video depth. However, naively applying a single-image depth estimator to every frame of a video disregards temporal continuity, which not only leads to flickering but may also break when camera motion causes sudden changes in depth range. An obvious and principled solution would be to build on top of video foundation models, but these come with their own limitations; including expensive training and inference, imperfect 3D consistency, and stitching routines for the fixed-length (short) outputs. We take a step back and demonstrate how to turn a single-image latent diffusion model (LDM) into a state-of-the-art video depth estimator. Our model, which we call RollingDepth, has two main ingredients: (i) a multi-frame depth estimator that is derived from a single-image LDM and maps very short video snippets (typically frame triplets) to depth snippets. (ii) a robust, optimization-based registration algorithm that optimally assembles depth snippets sampled at various different frame rates back into a consistent video. RollingDepth is able to efficiently handle long videos with hundreds of frames and delivers more accurate depth videos than both dedicated video depth estimators and high-performing single-frame models. Project page: rollingdepth.github.io.