Collaborative Learning for Unsupervised Multimodal Remote Sensing Image Registration: Integrating Self-Supervision and MIM-Guided Diffusion-Based Image Translation

The substantial modality-induced variations in radiometric, texture, and structural characteristics pose significant challenges for the accurate registration of multimodal images. While supervised deep learning methods have demonstrated strong performance, they often rely on large-scale annotated datasets, limiting their practical application. Traditional unsupervised methods usually optimize registration by minimizing differences in feature representations, yet often fail to robustly capture geometric discrepancies, particularly under substantial spatial and radiometric variations, thus hindering convergence stability. To address these challenges, we propose a Collaborative Learning framework for Unsupervised Multimodal Image Registration, named CoLReg, which reformulates unsupervised registration learning into a collaborative training paradigm comprising three components: (1) a cross-modal image translation network, MIMGCD, which employs a learnable Maximum Index Map (MIM) guided conditional diffusion model to synthesize modality-consistent image pairs; (2) a self-supervised intermediate registration network which learns to estimate geometric transformations using accurate displacement labels derived from MIMGCD outputs; (3) a distilled cross-modal registration network trained with pseudo-label predicted by the intermediate network. The three networks are jointly optimized through an alternating training strategy wherein each network enhances the performance of the others. This mutual collaboration progressively reduces modality discrepancies, enhances the quality of pseudo-labels, and improves registration accuracy. Extensive experimental results on multiple datasets demonstrate that our ColReg achieves competitive or superior performance compared to state-of-the-art unsupervised approaches and even surpasses several supervised baselines.

Score-based Generative Diffusion Models to Synthesize Full-dose FDG Brain PET from MRI in Epilepsy Patients

Fluorodeoxyglucose (FDG) PET to evaluate patients with epilepsy is one of the most common applications for simultaneous PET/MRI, given the need to image both brain structure and metabolism, but is suboptimal due to the radiation dose in this young population. Little work has been done synthesizing diagnostic quality PET images from MRI data or MRI data with ultralow-dose PET using advanced generative AI methods, such as diffusion models, with attention to clinical evaluations tailored for the epilepsy population. Here we compared the performance of diffusion- and non-diffusion-based deep learning models for the MRI-to-PET image translation task for epilepsy imaging using simultaneous PET/MRI in 52 subjects (40 train/2 validate/10 hold-out test). We tested three different models: 2 score-based generative diffusion models (SGM-Karras Diffusion [SGM-KD] and SGM-variance preserving [SGM-VP]) and a Transformer-Unet. We report results on standard image processing metrics as well as clinically relevant metrics, including congruency measures (Congruence Index and Congruency Mean Absolute Error) that assess hemispheric metabolic asymmetry, which is a key part of the clinical analysis of these images. The SGM-KD produced the best qualitative and quantitative results when synthesizing PET purely from T1w and T2 FLAIR images with the least mean absolute error in whole-brain specific uptake value ratio (SUVR) and highest intraclass correlation coefficient. When 1% low-dose PET images are included in the inputs, all models improve significantly and are interchangeable for quantitative performance and visual quality. In summary, SGMs hold great potential for pure MRI-to-PET translation, while all 3 model types can synthesize full-dose FDG-PET accurately using MRI and ultralow-dose PET.

Deep learning image burst stacking to reconstruct high-resolution ground-based solar observations

Large aperture ground based solar telescopes allow the solar atmosphere to be resolved in unprecedented detail. However, observations are limited by Earths turbulent atmosphere, requiring post image corrections. Current reconstruction methods using short exposure bursts face challenges with strong turbulence and high computational costs. We introduce a deep learning approach that reconstructs 100 short exposure images into one high quality image in real time. Using unpaired image to image translation, our model is trained on degraded bursts with speckle reconstructions as references, improving robustness and generalization. Our method shows an improved robustness in terms of perceptual quality, especially when speckle reconstructions show artifacts. An evaluation with a varying number of images per burst demonstrates that our method makes efficient use of the combined image information and achieves the best reconstructions when provided with the full image burst.

Demystifying the Visual Quality Paradox in Multimodal Large Language Models

Recent Multimodal Large Language Models (MLLMs) excel on benchmark vision-language tasks, yet little is known about how input visual quality shapes their responses. Does higher perceptual quality of images already translate to better MLLM understanding? We conduct the first systematic study spanning leading MLLMs and a suite of vision-language benchmarks, applying controlled degradations and stylistic shifts to each image. Surprisingly, we uncover a visual-quality paradox: model, task, and even individual-instance performance can improve when images deviate from human-perceived fidelity. Off-the-shelf restoration pipelines fail to reconcile these idiosyncratic preferences. To close the gap, we introduce Visual-Quality Test-Time Tuning (VQ-TTT)-a lightweight adaptation module that: (1) inserts a learnable, low-rank kernel before the frozen vision encoder to modulate frequency content; and (2) fine-tunes only shallow vision-encoder layers via LoRA. VQ-TTT dynamically adjusts each input image in a single forward pass, aligning it with task-specific model preferences. Across the evaluated MLLMs and all datasets, VQ-TTT lifts significant average accuracy, with no external models, cached features, or extra training data. These findings redefine ``better'' visual inputs for MLLMs and highlight the need for adaptive, rather than universally ``clean'', imagery, in the new era of AI being the main data customer.

SAR2Struct: Extracting 3D Semantic Structural Representation of Aircraft Targets from Single-View SAR Image

To translate synthetic aperture radar (SAR) image into interpretable forms for human understanding is the ultimate goal of SAR advanced information retrieval. Existing methods mainly focus on 3D surface reconstruction or local geometric feature extraction of targets, neglecting the role of structural modeling in capturing semantic information. This paper proposes a novel task: SAR target structure recovery, which aims to infer the components of a target and the structural relationships between its components, specifically symmetry and adjacency, from a single-view SAR image. Through learning the structural consistency and geometric diversity across the same type of targets as observed in different SAR images, it aims to derive the semantic representation of target directly from its 2D SAR image. To solve this challenging task, a two-step algorithmic framework based on structural descriptors is developed. Specifically, in the training phase, it first detects 2D keypoints from real SAR images, and then learns the mapping from these keypoints to 3D hierarchical structures using simulated data. During the testing phase, these two steps are integrated to infer the 3D structure from real SAR images. Experimental results validated the effectiveness of each step and demonstrated, for the first time, that 3D semantic structural representation of aircraft targets can be directly derived from a single-view SAR image.

General Methods Make Great Domain-specific Foundation Models: A Case-study on Fetal Ultrasound

With access to large-scale, unlabeled medical datasets, researchers are confronted with two questions: Should they attempt to pretrain a custom foundation model on this medical data, or use transfer-learning from an existing generalist model? And, if a custom model is pretrained, are novel methods required? In this paper we explore these questions by conducting a case-study, in which we train a foundation model on a large regional fetal ultrasound dataset of 2M images. By selecting the well-established DINOv2 method for pretraining, we achieve state-of-the-art results on three fetal ultrasound datasets, covering data from different countries, classification, segmentation, and few-shot tasks. We compare against a series of models pretrained on natural images, ultrasound images, and supervised baselines. Our results demonstrate two key insights: (i) Pretraining on custom data is worth it, even if smaller models are trained on less data, as scaling in natural image pretraining does not translate to ultrasound performance. (ii) Well-tuned methods from computer vision are making it feasible to train custom foundation models for a given medical domain, requiring no hyperparameter tuning and little methodological adaptation. Given these findings, we argue that a bias towards methodological innovation should be avoided when developing domain specific foundation models under common computational resource constraints.

NeoBabel: A Multilingual Open Tower for Visual Generation

Text-to-image generation advancements have been predominantly English-centric, creating barriers for non-English speakers and perpetuating digital inequities. While existing systems rely on translation pipelines, these introduce semantic drift, computational overhead, and cultural misalignment. We introduce NeoBabel, a novel multilingual image generation framework that sets a new Pareto frontier in performance, efficiency and inclusivity, supporting six languages: English, Chinese, Dutch, French, Hindi, and Persian. The model is trained using a combination of large-scale multilingual pretraining and high-resolution instruction tuning. To evaluate its capabilities, we expand two English-only benchmarks to multilingual equivalents: m-GenEval and m-DPG. NeoBabel achieves state-of-the-art multilingual performance while retaining strong English capability, scoring 0.75 on m-GenEval and 0.68 on m-DPG. Notably, it performs on par with leading models on English tasks while outperforming them by +0.11 and +0.09 on multilingual benchmarks, even though these models are built on multilingual base LLMs. This demonstrates the effectiveness of our targeted alignment training for preserving and extending crosslingual generalization. We further introduce two new metrics to rigorously assess multilingual alignment and robustness to code-mixed prompts. Notably, NeoBabel matches or exceeds English-only models while being 2-4x smaller. We release an open toolkit, including all code, model checkpoints, a curated dataset of 124M multilingual text-image pairs, and standardized multilingual evaluation protocols, to advance inclusive AI research. Our work demonstrates that multilingual capability is not a trade-off but a catalyst for improved robustness, efficiency, and cultural fidelity in generative AI.

ShapeEmbed: a self-supervised learning framework for 2D contour quantification

The shape of objects is an important source of visual information in a wide range of applications. One of the core challenges of shape quantification is to ensure that the extracted measurements remain invariant to transformations that preserve an object's intrinsic geometry, such as changing its size, orientation, and position in the image. In this work, we introduce ShapeEmbed, a self-supervised representation learning framework designed to encode the contour of objects in 2D images, represented as a Euclidean distance matrix, into a shape descriptor that is invariant to translation, scaling, rotation, reflection, and point indexing. Our approach overcomes the limitations of traditional shape descriptors while improving upon existing state-of-the-art autoencoder-based approaches. We demonstrate that the descriptors learned by our framework outperform their competitors in shape classification tasks on natural and biological images. We envision our approach to be of particular relevance to biological imaging applications.

UniLGL: Learning Uniform Place Recognition for FOV-limited/Panoramic LiDAR Global Localization

Existing LGL methods typically consider only partial information (e.g., geometric features) from LiDAR observations or are designed for homogeneous LiDAR sensors, overlooking the uniformity in LGL. In this work, a uniform LGL method is proposed, termed UniLGL, which simultaneously achieves spatial and material uniformity, as well as sensor-type uniformity. The key idea of the proposed method is to encode the complete point cloud, which contains both geometric and material information, into a pair of BEV images (i.e., a spatial BEV image and an intensity BEV image). An end-to-end multi-BEV fusion network is designed to extract uniform features, equipping UniLGL with spatial and material uniformity. To ensure robust LGL across heterogeneous LiDAR sensors, a viewpoint invariance hypothesis is introduced, which replaces the conventional translation equivariance assumption commonly used in existing LPR networks and supervises UniLGL to achieve sensor-type uniformity in both global descriptors and local feature representations. Finally, based on the mapping between local features on the 2D BEV image and the point cloud, a robust global pose estimator is derived that determines the global minimum of the global pose on SE(3) without requiring additional registration. To validate the effectiveness of the proposed uniform LGL, extensive benchmarks are conducted in real-world environments, and the results show that the proposed UniLGL is demonstratively competitive compared to other State-of-the-Art LGL methods. Furthermore, UniLGL has been deployed on diverse platforms, including full-size trucks and agile Micro Aerial Vehicles (MAVs), to enable high-precision localization and mapping as well as multi-MAV collaborative exploration in port and forest environments, demonstrating the applicability of UniLGL in industrial and field scenarios.

Rethinking Multilingual Vision-Language Translation: Dataset, Evaluation, and Adaptation

Vision-Language Translation (VLT) is a challenging task that requires accurately recognizing multilingual text embedded in images and translating it into the target language with the support of visual context. While recent Large Vision-Language Models (LVLMs) have demonstrated strong multilingual and visual understanding capabilities, there is a lack of systematic evaluation and understanding of their performance on VLT. In this work, we present a comprehensive study of VLT from three key perspectives: data quality, model architecture, and evaluation metrics. (1) We identify critical limitations in existing datasets, particularly in semantic and cultural fidelity, and introduce AibTrans -- a multilingual, parallel, human-verified dataset with OCR-corrected annotations. (2) We benchmark 11 commercial LVLMs/LLMs and 6 state-of-the-art open-source models across end-to-end and cascaded architectures, revealing their OCR dependency and contrasting generation versus reasoning behaviors. (3) We propose Density-Aware Evaluation to address metric reliability issues under varying contextual complexity, introducing the DA Score as a more robust measure of translation quality. Building upon these findings, we establish a new evaluation benchmark for VLT. Notably, we observe that fine-tuning LVLMs on high-resource language pairs degrades cross-lingual performance, and we propose a balanced multilingual fine-tuning strategy that effectively adapts LVLMs to VLT without sacrificing their generalization ability.