HawkI: Homography & Mutual Information Guidance for 3D-free Single Image to Aerial View

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: Kothandaraman, Divya, Zhou, Tianyi, Lin, Ming, Manocha, Dinesh
Natura: Preprint
Pubblicazione: 2023
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866916357662048256
author Kothandaraman, Divya
Zhou, Tianyi
Lin, Ming
Manocha, Dinesh
author_facet Kothandaraman, Divya
Zhou, Tianyi
Lin, Ming
Manocha, Dinesh
contents We present HawkI, for synthesizing aerial-view images from text and an exemplar image, without any additional multi-view or 3D information for finetuning or at inference. HawkI uses techniques from classical computer vision and information theory. It seamlessly blends the visual features from the input image within a pretrained text-to-2Dimage stable diffusion model with a test-time optimization process for a careful bias-variance trade-off, which uses an Inverse Perspective Mapping (IPM) homography transformation to provide subtle cues for aerialview synthesis. At inference, HawkI employs a unique mutual information guidance formulation to steer the generated image towards faithfully replicating the semantic details of the input-image, while maintaining a realistic aerial perspective. Mutual information guidance maximizes the semantic consistency between the generated image and the input image, without enforcing pixel-level correspondence between vastly different viewpoints. Through extensive qualitative and quantitative comparisons against text + exemplar-image based methods and 3D/ multi-view based novel-view synthesis methods on proposed synthetic and real datasets, we demonstrate that our method achieves a significantly better bias-variance trade-off towards generating high fidelity aerial-view images.Code and data is available at https://github.com/divyakraman/HawkI2024.
format Preprint
id arxiv_https___arxiv_org_abs_2311_15478
institution arXiv
publishDate 2023
record_format arxiv
spellingShingle HawkI: Homography & Mutual Information Guidance for 3D-free Single Image to Aerial View
Kothandaraman, Divya
Zhou, Tianyi
Lin, Ming
Manocha, Dinesh
Computer Vision and Pattern Recognition
We present HawkI, for synthesizing aerial-view images from text and an exemplar image, without any additional multi-view or 3D information for finetuning or at inference. HawkI uses techniques from classical computer vision and information theory. It seamlessly blends the visual features from the input image within a pretrained text-to-2Dimage stable diffusion model with a test-time optimization process for a careful bias-variance trade-off, which uses an Inverse Perspective Mapping (IPM) homography transformation to provide subtle cues for aerialview synthesis. At inference, HawkI employs a unique mutual information guidance formulation to steer the generated image towards faithfully replicating the semantic details of the input-image, while maintaining a realistic aerial perspective. Mutual information guidance maximizes the semantic consistency between the generated image and the input image, without enforcing pixel-level correspondence between vastly different viewpoints. Through extensive qualitative and quantitative comparisons against text + exemplar-image based methods and 3D/ multi-view based novel-view synthesis methods on proposed synthetic and real datasets, we demonstrate that our method achieves a significantly better bias-variance trade-off towards generating high fidelity aerial-view images.Code and data is available at https://github.com/divyakraman/HawkI2024.
title HawkI: Homography & Mutual Information Guidance for 3D-free Single Image to Aerial View
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2311.15478