Saved in:
Bibliographic Details
Main Authors: Talegaonkar, Chinmay, Suresh, Nikhil Gandudi, Novack, Zachary, Belhe, Yash, Nagasamudra, Priyanka, Antipa, Nicholas
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2505.17358
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866915300425859072
author Talegaonkar, Chinmay
Suresh, Nikhil Gandudi
Novack, Zachary
Belhe, Yash
Nagasamudra, Priyanka
Antipa, Nicholas
author_facet Talegaonkar, Chinmay
Suresh, Nikhil Gandudi
Novack, Zachary
Belhe, Yash
Nagasamudra, Priyanka
Antipa, Nicholas
contents Recent monocular metric depth estimation (MMDE) methods have made notable progress towards zero-shot generalization. However, they still exhibit a significant performance drop on out-of-distribution datasets. We address this limitation by injecting defocus blur cues at inference time into Marigold, a \textit{pre-trained} diffusion model for zero-shot, scale-invariant monocular depth estimation (MDE). Our method effectively turns Marigold into a metric depth predictor in a training-free manner. To incorporate defocus cues, we capture two images with a small and a large aperture from the same viewpoint. To recover metric depth, we then optimize the metric depth scaling parameters and the noise latents of Marigold at inference time using gradients from a loss function based on the defocus-blur image formation model. We compare our method against existing state-of-the-art zero-shot MMDE methods on a self-collected real dataset, showing quantitative and qualitative improvements.
format Preprint
id arxiv_https___arxiv_org_abs_2505_17358
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Repurposing Marigold for Zero-Shot Metric Depth Estimation via Defocus Blur Cues
Talegaonkar, Chinmay
Suresh, Nikhil Gandudi
Novack, Zachary
Belhe, Yash
Nagasamudra, Priyanka
Antipa, Nicholas
Computer Vision and Pattern Recognition
Recent monocular metric depth estimation (MMDE) methods have made notable progress towards zero-shot generalization. However, they still exhibit a significant performance drop on out-of-distribution datasets. We address this limitation by injecting defocus blur cues at inference time into Marigold, a \textit{pre-trained} diffusion model for zero-shot, scale-invariant monocular depth estimation (MDE). Our method effectively turns Marigold into a metric depth predictor in a training-free manner. To incorporate defocus cues, we capture two images with a small and a large aperture from the same viewpoint. To recover metric depth, we then optimize the metric depth scaling parameters and the noise latents of Marigold at inference time using gradients from a loss function based on the defocus-blur image formation model. We compare our method against existing state-of-the-art zero-shot MMDE methods on a self-collected real dataset, showing quantitative and qualitative improvements.
title Repurposing Marigold for Zero-Shot Metric Depth Estimation via Defocus Blur Cues
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2505.17358