DVD: Deterministic Video Depth Estimation with Generative Priors
This work addresses the problem of accurate and efficient video depth estimation for computer vision applications, representing a novel method for a known bottleneck rather than an incremental improvement.
The paper tackled the trade-off between stochastic geometric hallucinations in generative models and the need for large labeled datasets in discriminative models for video depth estimation by introducing DVD, a framework that adapts pre-trained video diffusion models into deterministic depth regressors, achieving state-of-the-art zero-shot performance and using 163x less task-specific data than baselines.
Existing video depth estimation faces a fundamental trade-off: generative models suffer from stochastic geometric hallucinations and scale drift, while discriminative models demand massive labeled datasets to resolve semantic ambiguities. To break this impasse, we present DVD, the first framework to deterministically adapt pre-trained video diffusion models into single-pass depth regressors. Specifically, DVD features three core designs: (i) repurposing the diffusion timestep as a structural anchor to balance global stability with high-frequency details; (ii) latent manifold rectification (LMR) to mitigate regression-induced over-smoothing, enforcing differential constraints to restore sharp boundaries and coherent motion; and (iii) global affine coherence, an inherent property bounding inter-window divergence, which enables seamless long-video inference without requiring complex temporal alignment. Extensive experiments demonstrate that DVD achieves state-of-the-art zero-shot performance across benchmarks. Furthermore, DVD successfully unlocks the profound geometric priors implicit in video foundation models using 163x less task-specific data than leading baselines. Notably, we fully release our pipeline, providing the whole training suite for SOTA video depth estimation to benefit the open-source community.