ThermoSplat: Cross-Modal 3D Gaussian Splatting with Feature Modulation and Geometry Decoupling

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: Su, Zhaoqi, Chen, Shihai, Lin, Xinyan, Huang, Liqin, Su, Zhipeng, Lu, Xiaoqiang
Natura: Preprint
Pubblicazione: 2026
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866917258865934336
author Su, Zhaoqi
Chen, Shihai
Lin, Xinyan
Huang, Liqin
Su, Zhipeng
Lu, Xiaoqiang
author_facet Su, Zhaoqi
Chen, Shihai
Lin, Xinyan
Huang, Liqin
Su, Zhipeng
Lu, Xiaoqiang
contents Multi-modal scene reconstruction integrating RGB and thermal infrared data is essential for robust environmental perception across diverse lighting and weather conditions. However, extending 3D Gaussian Splatting (3DGS) to multi-spectral scenarios remains challenging. Current approaches often struggle to fully leverage the complementary information of multi-modal data, typically relying on mechanisms that either tend to neglect cross-modal correlations or leverage shared representations that fail to adaptively handle the complex structural correlations and physical discrepancies between spectrums. To address these limitations, we propose ThermoSplat, a novel framework that enables deep spectral-aware reconstruction through active feature modulation and adaptive geometry decoupling. First, we introduce a Spectrum-Aware Adaptive Modulation that dynamically conditions shared latent features on thermal structural priors, effectively guiding visible texture synthesis with reliable cross-modal geometric cues. Second, to accommodate modality-specific geometric inconsistencies, we propose a Modality-Adaptive Geometric Decoupling scheme that learns independent opacity offsets and executes an independent rasterization pass for the thermal branch. Additionally, a hybrid rendering pipeline is employed to integrate explicit Spherical Harmonics with implicit neural decoding, ensuring both semantic consistency and high-frequency detail preservation. Extensive experiments on the RGBT-Scenes dataset demonstrate that ThermoSplat achieves state-of-the-art rendering quality across both visible and thermal spectrums.
format Preprint
id arxiv_https___arxiv_org_abs_2601_15897
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle ThermoSplat: Cross-Modal 3D Gaussian Splatting with Feature Modulation and Geometry Decoupling
Su, Zhaoqi
Chen, Shihai
Lin, Xinyan
Huang, Liqin
Su, Zhipeng
Lu, Xiaoqiang
Computer Vision and Pattern Recognition
Multi-modal scene reconstruction integrating RGB and thermal infrared data is essential for robust environmental perception across diverse lighting and weather conditions. However, extending 3D Gaussian Splatting (3DGS) to multi-spectral scenarios remains challenging. Current approaches often struggle to fully leverage the complementary information of multi-modal data, typically relying on mechanisms that either tend to neglect cross-modal correlations or leverage shared representations that fail to adaptively handle the complex structural correlations and physical discrepancies between spectrums. To address these limitations, we propose ThermoSplat, a novel framework that enables deep spectral-aware reconstruction through active feature modulation and adaptive geometry decoupling. First, we introduce a Spectrum-Aware Adaptive Modulation that dynamically conditions shared latent features on thermal structural priors, effectively guiding visible texture synthesis with reliable cross-modal geometric cues. Second, to accommodate modality-specific geometric inconsistencies, we propose a Modality-Adaptive Geometric Decoupling scheme that learns independent opacity offsets and executes an independent rasterization pass for the thermal branch. Additionally, a hybrid rendering pipeline is employed to integrate explicit Spherical Harmonics with implicit neural decoding, ensuring both semantic consistency and high-frequency detail preservation. Extensive experiments on the RGBT-Scenes dataset demonstrate that ThermoSplat achieves state-of-the-art rendering quality across both visible and thermal spectrums.
title ThermoSplat: Cross-Modal 3D Gaussian Splatting with Feature Modulation and Geometry Decoupling
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2601.15897