GRIN: Zero-Shot Metric Depth with Pixel-Level Diffusion

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Guizilini, Vitor, Tokmakov, Pavel, Dave, Achal, Ambrus, Rares
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866913501329489920
author Guizilini, Vitor
Tokmakov, Pavel
Dave, Achal
Ambrus, Rares
author_facet Guizilini, Vitor
Tokmakov, Pavel
Dave, Achal
Ambrus, Rares
contents 3D reconstruction from a single image is a long-standing problem in computer vision. Learning-based methods address its inherent scale ambiguity by leveraging increasingly large labeled and unlabeled datasets, to produce geometric priors capable of generating accurate predictions across domains. As a result, state of the art approaches show impressive performance in zero-shot relative and metric depth estimation. Recently, diffusion models have exhibited remarkable scalability and generalizable properties in their learned representations. However, because these models repurpose tools originally designed for image generation, they can only operate on dense ground-truth, which is not available for most depth labels, especially in real-world settings. In this paper we present GRIN, an efficient diffusion model designed to ingest sparse unstructured training data. We use image features with 3D geometric positional encodings to condition the diffusion process both globally and locally, generating depth predictions at a pixel-level. With comprehensive experiments across eight indoor and outdoor datasets, we show that GRIN establishes a new state of the art in zero-shot metric monocular depth estimation even when trained from scratch.
format Preprint
id arxiv_https___arxiv_org_abs_2409_09896
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle GRIN: Zero-Shot Metric Depth with Pixel-Level Diffusion
Guizilini, Vitor
Tokmakov, Pavel
Dave, Achal
Ambrus, Rares
Computer Vision and Pattern Recognition
Machine Learning
Image and Video Processing
3D reconstruction from a single image is a long-standing problem in computer vision. Learning-based methods address its inherent scale ambiguity by leveraging increasingly large labeled and unlabeled datasets, to produce geometric priors capable of generating accurate predictions across domains. As a result, state of the art approaches show impressive performance in zero-shot relative and metric depth estimation. Recently, diffusion models have exhibited remarkable scalability and generalizable properties in their learned representations. However, because these models repurpose tools originally designed for image generation, they can only operate on dense ground-truth, which is not available for most depth labels, especially in real-world settings. In this paper we present GRIN, an efficient diffusion model designed to ingest sparse unstructured training data. We use image features with 3D geometric positional encodings to condition the diffusion process both globally and locally, generating depth predictions at a pixel-level. With comprehensive experiments across eight indoor and outdoor datasets, we show that GRIN establishes a new state of the art in zero-shot metric monocular depth estimation even when trained from scratch.
title GRIN: Zero-Shot Metric Depth with Pixel-Level Diffusion
topic Computer Vision and Pattern Recognition
Machine Learning
Image and Video Processing
url https://arxiv.org/abs/2409.09896