{"ID":2831536,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2512.07230","arxiv_id":"2512.07230","title":"STRinGS: Selective Text Refinement in Gaussian Splatting","abstract":"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.","short_abstract":"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 reconstruct...","url_abs":"https://arxiv.org/abs/2512.07230","url_pdf":"https://arxiv.org/pdf/2512.07230v1","authors":"[\"Abhinav Raundhal\",\"Gaurav Behera\",\"P J Narayanan\",\"Ravi Kiran Sarvadevabhatla\",\"Makarand Tapaswi\"]","published":"2025-12-08T07:20:01Z","proceeding":"cs.CV","tasks":"[\"cs.CV\"]","methods":"[]","has_code":false}