Skel3D: Skeleton Guided Novel View Synthesis

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Fóthi, Aron, Fazekas, Bence, Gyöngyössy, Natabara Máté, Fenech, Kristian
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866910727130841088
author Fóthi, Aron
Fazekas, Bence
Gyöngyössy, Natabara Máté
Fenech, Kristian
author_facet Fóthi, Aron
Fazekas, Bence
Gyöngyössy, Natabara Máté
Fenech, Kristian
contents In this paper, we present an approach for monocular open-set novel view synthesis (NVS) that leverages object skeletons to guide the underlying diffusion model. Building upon a baseline that utilizes a pre-trained 2D image generator, our method takes advantage of the Objaverse dataset, which includes animated objects with bone structures. By introducing a skeleton guide layer following the existing ray conditioning normalization (RCN) layer, our approach enhances pose accuracy and multi-view consistency. The skeleton guide layer provides detailed structural information for the generative model, improving the quality of synthesized views. Experimental results demonstrate that our skeleton-guided method significantly enhances consistency and accuracy across diverse object categories within the Objaverse dataset. Our method outperforms existing state-of-the-art NVS techniques both quantitatively and qualitatively, without relying on explicit 3D representations.
format Preprint
id arxiv_https___arxiv_org_abs_2412_03407
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Skel3D: Skeleton Guided Novel View Synthesis
Fóthi, Aron
Fazekas, Bence
Gyöngyössy, Natabara Máté
Fenech, Kristian
Computer Vision and Pattern Recognition
In this paper, we present an approach for monocular open-set novel view synthesis (NVS) that leverages object skeletons to guide the underlying diffusion model. Building upon a baseline that utilizes a pre-trained 2D image generator, our method takes advantage of the Objaverse dataset, which includes animated objects with bone structures. By introducing a skeleton guide layer following the existing ray conditioning normalization (RCN) layer, our approach enhances pose accuracy and multi-view consistency. The skeleton guide layer provides detailed structural information for the generative model, improving the quality of synthesized views. Experimental results demonstrate that our skeleton-guided method significantly enhances consistency and accuracy across diverse object categories within the Objaverse dataset. Our method outperforms existing state-of-the-art NVS techniques both quantitatively and qualitatively, without relying on explicit 3D representations.
title Skel3D: Skeleton Guided Novel View Synthesis
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2412.03407