# SEAR: Simple and Efficient Adaptation of Visual Geometric Transformers for Unpaired RGB+Thermal 3D Reconstruction

arXiv: https://arxiv.org/abs/2603.18774 · HTML: https://mlsanity.com/paper/2603.18774/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 30 of its 51 references that are in the map.
- First posted on arXiv 19 Mar 2026.

## Builds on (most cited first, 30 of 30)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [LoRA: Low-Rank Adaptation of Large Language Models](https://mlsanity.com/paper/2106.09685/) (2021)
- [DINOv2: Learning Robust Visual Features without Supervision](https://mlsanity.com/paper/2304.07193/) (2023)
- [Visual Instruction Tuning](https://mlsanity.com/paper/2304.08485/) (2023)
- [Parameter-Efficient Transfer Learning for NLP](https://mlsanity.com/paper/1902.00751/) (2019)
- [The Power of Scale for Parameter-Efficient Prompt Tuning](https://mlsanity.com/paper/2104.08691/) (2021)
- [DUSt3R: Geometric 3D Vision Made Easy](https://mlsanity.com/paper/2312.14132/) (2023)
- [VGGT: Visual Geometry Grounded Transformer](https://mlsanity.com/paper/2503.11651/) (2025)
- [SuperGlue: Learning Feature Matching with Graph Neural Networks](https://mlsanity.com/paper/1911.11763/) (2019)
- [ORB-SLAM: a Versatile and Accurate Monocular SLAM System](https://mlsanity.com/paper/1502.00956/) (2015)
- [Grounding Image Matching in 3D with MASt3R](https://mlsanity.com/paper/2406.09756/) (2024)
- [RoMa: Robust Dense Feature Matching](https://mlsanity.com/paper/2305.15404/) (2023)
- [Efficient LoFTR: Semi-Dense Local Feature Matching with Sparse-Like Speed](https://mlsanity.com/paper/2403.04765/) (2024)
- [Understanding and Mitigating Numerical Sources of Nondeterminism in LLM Inference](https://mlsanity.com/paper/2506.09501/) (2025)
- [XoFTR: Cross-modal Feature Matching Transformer](https://mlsanity.com/paper/2404.09692/) (2024)
- [MINIMA: Modality Invariant Image Matching](https://mlsanity.com/paper/2412.19412/) (2024)
- [Light3R-SfM: Towards Feed-forward Structure-from-Motion](https://mlsanity.com/paper/2501.14914/) (2025)
- [MatchAnything: Universal Cross-Modality Image Matching with Large-Scale Pre-Training](https://mlsanity.com/paper/2501.07556/) (2025)
- [ViViD++: Vision for Visibility Dataset](https://mlsanity.com/paper/2204.06183/) (2022)
- [MP-SfM: Monocular Surface Priors for Robust Structure-from-Motion](https://mlsanity.com/paper/2504.20040/) (2025)
- [Emergent Outlier View Rejection in Visual Geometry Grounded Transformers](https://mlsanity.com/paper/2512.04012/) (2025)
- [Exploring Multi-modal Neural Scene Representations With Applications on Thermal Imaging](https://mlsanity.com/paper/2403.11865/) (2024)
- [High-Fidelity SLAM Using Gaussian Splatting with Rendering-Guided Densification and Regularized Optimization](https://mlsanity.com/paper/2403.12535/) (2024)
- [Spec-NeRF: Multi-spectral Neural Radiance Fields](https://mlsanity.com/paper/2310.12987/) (2023)
- [ThermalNeRF: Thermal Radiance Fields](https://mlsanity.com/paper/2407.15337/) (2024)
- [Leveraging Thermal Modality to Enhance Reconstruction in Low-Light Conditions](https://mlsanity.com/paper/2403.14053/) (2024)
- [On Geometric Understanding and Learned Priors in Feed-forward 3D Reconstruction Models](https://mlsanity.com/paper/2512.11508/) (2025)
- [SmokeSeer: 3D Gaussian Splatting for Smoke Removal and Scene Reconstruction](https://mlsanity.com/paper/2509.17329/) (2025)
- [Thermoxels: a voxel-based method to generate simulation-ready 3D thermal models](https://mlsanity.com/paper/2504.04448/) (2025)
- [Empower Vision Applications with LoRA LMM](https://mlsanity.com/paper/2411.00915/) (2024)

## Built on by (most cited first, 2 of 2)

- [DarkVGGT: Seeing Through Darkness Using Thermal Geometry](https://mlsanity.com/paper/2606.11326/) (2026)
- [Spline-Based Boundary Representations for Sparse View Reconstruction and Simulation Using Isogeometric Analysis](https://mlsanity.com/paper/2607.26234/) (2026)

## Abstract (arXiv)

Foundational feed-forward visual geometry models enable accurate and efficient camera pose estimation and scene reconstruction by learning strong scene priors from massive RGB datasets. However, their effectiveness drops when applied to mixed sensing modalities, such as RGB-thermal (RGB-T) images. We observe that while a visual geometry grounded transformer pretrained on RGB data generalizes well to thermal-only reconstruction, it struggles to align RGB and thermal modalities when processed jointly. To address this, we propose SEAR, a simple yet efficient fine-tuning strategy that adapts a pretrained geometry transformer to multimodal RGB-T inputs. Despite being trained on a relatively small RGB-T dataset, our approach significantly outperforms state-of-the-art methods for 3D reconstruction and camera pose estimation, achieving significant improvements over all metrics and delivering higher detail and consistency between modalities with negligible overhead in inference time compared to the original pretrained model. Notably, SEAR enables reliable multimodal pose estimation and reconstruction even under challenging conditions, such as low lighting and dense smoke. We validate our architecture through extensive ablation studies and demonstrate how the model aligns both modalities. Additionally, we introduce a new dataset featuring RGB and thermal sequences captured at different times, viewpoints, and illumination conditions, providing a robust benchmark for future work in multimodal 3D scene reconstruction. Code and models are publicly available at https://doi.org/10.5281/ZENODO.21077295.