Dust to Tower: Coarse-to-Fine Photo-Realistic Scene Reconstruction from Sparse Uncalibrated Images

Fuente: arXiv
Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Cai, Xudong, Wang, Yongcai, Fan, Zhaoxin, Haoran, Deng, Wang, Shuo, Li, Wanting, Li, Deying, Luo, Lun, Wang, Minhang, Xu, Jintao
Format: Preprint
Veröffentlicht: 2024
Schlagworte:
Online-Zugang:
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866912170379313152
author Cai, Xudong
Wang, Yongcai
Fan, Zhaoxin
Haoran, Deng
Wang, Shuo
Li, Wanting
Li, Deying
Luo, Lun
Wang, Minhang
Xu, Jintao
author_facet Cai, Xudong
Wang, Yongcai
Fan, Zhaoxin
Haoran, Deng
Wang, Shuo
Li, Wanting
Li, Deying
Luo, Lun
Wang, Minhang
Xu, Jintao
contents Photo-realistic scene reconstruction from sparse-view, uncalibrated images is highly required in practice. Although some successes have been made, existing methods are either Sparse-View but require accurate camera parameters (i.e., intrinsic and extrinsic), or SfM-free but need densely captured images. To combine the advantages of both methods while addressing their respective weaknesses, we propose Dust to Tower (D2T), an accurate and efficient coarse-to-fine framework to optimize 3DGS and image poses simultaneously from sparse and uncalibrated images. Our key idea is to first construct a coarse model efficiently and subsequently refine it using warped and inpainted images at novel viewpoints. To do this, we first introduce a Coarse Construction Module (CCM) which exploits a fast Multi-View Stereo model to initialize a 3D Gaussian Splatting (3DGS) and recover initial camera poses. To refine the 3D model at novel viewpoints, we propose a Confidence Aware Depth Alignment (CADA) module to refine the coarse depth maps by aligning their confident parts with estimated depths by a Mono-depth model. Then, a Warped Image-Guided Inpainting (WIGI) module is proposed to warp the training images to novel viewpoints by the refined depth maps, and inpainting is applied to fulfill the ``holes" in the warped images caused by view-direction changes, providing high-quality supervision to further optimize the 3D model and the camera poses. Extensive experiments and ablation studies demonstrate the validity of D2T and its design choices, achieving state-of-the-art performance in both tasks of novel view synthesis and pose estimation while keeping high efficiency. Codes will be publicly available.
format Preprint
id arxiv_https___arxiv_org_abs_2412_19518
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Dust to Tower: Coarse-to-Fine Photo-Realistic Scene Reconstruction from Sparse Uncalibrated Images
Cai, Xudong
Wang, Yongcai
Fan, Zhaoxin
Haoran, Deng
Wang, Shuo
Li, Wanting
Li, Deying
Luo, Lun
Wang, Minhang
Xu, Jintao
Computer Vision and Pattern Recognition
Photo-realistic scene reconstruction from sparse-view, uncalibrated images is highly required in practice. Although some successes have been made, existing methods are either Sparse-View but require accurate camera parameters (i.e., intrinsic and extrinsic), or SfM-free but need densely captured images. To combine the advantages of both methods while addressing their respective weaknesses, we propose Dust to Tower (D2T), an accurate and efficient coarse-to-fine framework to optimize 3DGS and image poses simultaneously from sparse and uncalibrated images. Our key idea is to first construct a coarse model efficiently and subsequently refine it using warped and inpainted images at novel viewpoints. To do this, we first introduce a Coarse Construction Module (CCM) which exploits a fast Multi-View Stereo model to initialize a 3D Gaussian Splatting (3DGS) and recover initial camera poses. To refine the 3D model at novel viewpoints, we propose a Confidence Aware Depth Alignment (CADA) module to refine the coarse depth maps by aligning their confident parts with estimated depths by a Mono-depth model. Then, a Warped Image-Guided Inpainting (WIGI) module is proposed to warp the training images to novel viewpoints by the refined depth maps, and inpainting is applied to fulfill the ``holes" in the warped images caused by view-direction changes, providing high-quality supervision to further optimize the 3D model and the camera poses. Extensive experiments and ablation studies demonstrate the validity of D2T and its design choices, achieving state-of-the-art performance in both tasks of novel view synthesis and pose estimation while keeping high efficiency. Codes will be publicly available.
title Dust to Tower: Coarse-to-Fine Photo-Realistic Scene Reconstruction from Sparse Uncalibrated Images
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2412.19518