Saved in:
Bibliographic Details
Main Authors: Zhang, Yufan, Ji, Yu, Guo, Yu, Ye, Jinwei
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2503.00260
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866917967667658752
author Zhang, Yufan
Ji, Yu
Guo, Yu
Ye, Jinwei
author_facet Zhang, Yufan
Ji, Yu
Guo, Yu
Ye, Jinwei
contents We present a snapshot imaging technique for recovering 3D surrounding views of miniature scenes. Due to their intricacy, miniature scenes with objects sized in millimeters are difficult to reconstruct, yet miniatures are common in life and their 3D digitalization is desirable. We design a catadioptric imaging system with a single camera and eight pairs of planar mirrors for snapshot 3D reconstruction from a dollhouse perspective. We place paired mirrors on nested pyramid surfaces for capturing surrounding multi-view images in a single shot. Our mirror design is customizable based on the size of the scene for optimized view coverage. We use the 3D Gaussian Splatting (3DGS) representation for scene reconstruction and novel view synthesis. We overcome the challenge posed by our sparse view input by integrating visual hull-derived depth constraint. Our method demonstrates state-of-the-art performance on a variety of synthetic and real miniature scenes.
format Preprint
id arxiv_https___arxiv_org_abs_2503_00260
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Seeing A 3D World in A Grain of Sand
Zhang, Yufan
Ji, Yu
Guo, Yu
Ye, Jinwei
Computer Vision and Pattern Recognition
We present a snapshot imaging technique for recovering 3D surrounding views of miniature scenes. Due to their intricacy, miniature scenes with objects sized in millimeters are difficult to reconstruct, yet miniatures are common in life and their 3D digitalization is desirable. We design a catadioptric imaging system with a single camera and eight pairs of planar mirrors for snapshot 3D reconstruction from a dollhouse perspective. We place paired mirrors on nested pyramid surfaces for capturing surrounding multi-view images in a single shot. Our mirror design is customizable based on the size of the scene for optimized view coverage. We use the 3D Gaussian Splatting (3DGS) representation for scene reconstruction and novel view synthesis. We overcome the challenge posed by our sparse view input by integrating visual hull-derived depth constraint. Our method demonstrates state-of-the-art performance on a variety of synthetic and real miniature scenes.
title Seeing A 3D World in A Grain of Sand
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2503.00260