STRinGS: Selective Text Refinement in Gaussian Splatting

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Raundhal, Abhinav, Behera, Gaurav, Narayanan, P J, Sarvadevabhatla, Ravi Kiran, Tapaswi, Makarand
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866914186336927744
author Raundhal, Abhinav
Behera, Gaurav
Narayanan, P J
Sarvadevabhatla, Ravi Kiran
Tapaswi, Makarand
author_facet Raundhal, Abhinav
Behera, Gaurav
Narayanan, P J
Sarvadevabhatla, Ravi Kiran
Tapaswi, Makarand
contents Text as signs, labels, or instructions is a critical element of real-world scenes as they can convey important contextual information. 3D representations such as 3D Gaussian Splatting (3DGS) struggle to preserve fine-grained text details, while achieving high visual fidelity. Small errors in textual element reconstruction can lead to significant semantic loss. We propose STRinGS, a text-aware, selective refinement framework to address this issue for 3DGS reconstruction. Our method treats text and non-text regions separately, refining text regions first and merging them with non-text regions later for full-scene optimization. STRinGS produces sharp, readable text even in challenging configurations. We introduce a text readability measure OCR Character Error Rate (CER) to evaluate the efficacy on text regions. STRinGS results in a 63.6% relative improvement over 3DGS at just 7K iterations. We also introduce a curated dataset STRinGS-360 with diverse text scenarios to evaluate text readability in 3D reconstruction. Our method and dataset together push the boundaries of 3D scene understanding in text-rich environments, paving the way for more robust text-aware reconstruction methods.
format Preprint
id arxiv_https___arxiv_org_abs_2512_07230
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle STRinGS: Selective Text Refinement in Gaussian Splatting
Raundhal, Abhinav
Behera, Gaurav
Narayanan, P J
Sarvadevabhatla, Ravi Kiran
Tapaswi, Makarand
Computer Vision and Pattern Recognition
Text as signs, labels, or instructions is a critical element of real-world scenes as they can convey important contextual information. 3D representations such as 3D Gaussian Splatting (3DGS) struggle to preserve fine-grained text details, while achieving high visual fidelity. Small errors in textual element reconstruction can lead to significant semantic loss. We propose STRinGS, a text-aware, selective refinement framework to address this issue for 3DGS reconstruction. Our method treats text and non-text regions separately, refining text regions first and merging them with non-text regions later for full-scene optimization. STRinGS produces sharp, readable text even in challenging configurations. We introduce a text readability measure OCR Character Error Rate (CER) to evaluate the efficacy on text regions. STRinGS results in a 63.6% relative improvement over 3DGS at just 7K iterations. We also introduce a curated dataset STRinGS-360 with diverse text scenarios to evaluate text readability in 3D reconstruction. Our method and dataset together push the boundaries of 3D scene understanding in text-rich environments, paving the way for more robust text-aware reconstruction methods.
title STRinGS: Selective Text Refinement in Gaussian Splatting
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2512.07230