Dec 2026· IEEE Robotics and Automation Letters· Vol 11, pp. 14788-14795· 0 citations· 45 references
TL;DR
This work introduces the Cross-Modality Diffusion framework, which explicitly translates visible keypoint features into the infrared feature space using conditional diffusion models and employs multi-objective training that combines diffusion reconstruction with feature alignment and matching consistency, together with classifier-free guidance during inference.
Abstract
Cross-modality image matching between visible and infrared spectra faces a key challenge: the substantial appearance discrepancies stemming from their distinct physical origins—texture and color in visible imagery versus thermal radiation in infrared. Existing approaches predominantly pursue modality-invariant representations through contrastive learning, domain adaptation, or generative data augmentation, aiming to reduce modality discrepancies within a shared embedding space. In this work, we investigate explicit modality translation as an alternative to modality-invariant representation learning. We introduce the Cross-Modality Diffusion (CMD) framework, which explicitly translates visible keypoint features into the infrared feature space using conditional diffusion models. CMD formulates feature translation as learning the conditional distribution $p(F_{i}|F_{v})$ through an iterative generative process. Through spatial positional encodings, the reverse diffusion process effectively transforms noise into infrared-like features under visible feature guidance, while preserving the spatial structure required for correspondence estimation. We employ multi-objective training that combines diffusion reconstruction with feature alignment and matching consistency, together with classifier-free guidance during inference. Extensive in-domain and zero-shot experiments demonstrate improved sparse correspondence estimation under substantial cross-modal appearance variations. Among the evaluated modular pipelines with frozen feature extractors and matchers, CMD achieves effective matching performance without requiring full retraining.
The results are packaged in the Greenfield Startup Model (GSM), which explains the priority of startups to release the product as quickly as possible, and the need to shorten time-to-market, by speeding up the development through low-precision engineering activities.
Carmine Giardino, Nicolò Paternoster, M. Unterkalmsteiner et al.· IEEE Transactions on Softwar...· 178 citations· ⚡14
Software startup companies develop innovative, software-intensive products within limited timeframes and with few resources, searching for sustainable and scalable business models.
M. Unterkalmsteiner, P. Abrahamsson, Xiaofeng Wang et al.· e-Informatica Software Engin...· 157 citations· ⚡17
This study conducts a case survey study based on the secondary data of the major pivots happened in 49 software startups, and demonstrates that customer need pivot is the most common among all pivot types.
Sohaib Shahid Bajwa, Xiaofeng Wang, Anh Nguyen-Duc et al.· Empirical Software Engineeri...· 127 citations· ⚡15
The comparison of adopter and non-adopter sample reveals three potential adoption inhibitor, security, data privacy, and portability, which underlines the importance of the technical and security perspectives for research investigating the adoption of technology.
Nattakarn Phaphoom, Xiaofeng Wang, S. Samuel et al.· Journal of Systems and Softw...· 111 citations· ⚡8
Objective There is dearth of information on the timeliness of antenatal care (ANC) uptake. This study aimed to determine the timely ANC uptake by a medically trained provider (MTP) as per the World Health Organization (WHO) recommendations and the country guideline. Methods Cross-sectional survey was done with 2,731 wo...
B. Sarker, Musfikur Rahman, T. Rahman et al.· PLoS ONE· 89 citations· ⚡7
This study investigates how Lean internal startup facilitates software product innovation in large companies and identifies its enablers and inhibitors, and shows the potential of the method-in-action framework to investigate the Lean startup approach in non-startup context.
Henry Edison, Nina M. Smørsgård, Xiaofeng Wang et al.· Journal of Systems and Softw...· 78 citations· ⚡6
Related blog posts
MIT News · Artificial Intelligence· news.mit.eduNov 20, 2026
Senior Research Scientist Jim Glass discusses how his MIT-IBM Computing Research Lab collaboration connects perception and language, and addresses the shortcoming of current models.
MIT News · Artificial Intelligence· news.mit.eduNov 20, 2026
Enforcing physics-based constraints prevents AI models from generating unreliable predictions for complex nonlinear systems in weather, climate, and turbulent flows.
An MIT and Dana-Farber Institute-led team used large language models to examine nearly 4,000 studies and hundreds of code repositories, revealing gaps in the information needed to scrutinize and reuse published research.
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.