arXiv:2511.16542v1 Announce Type: new 
Abstract: Recently, 3D Gaussian Splatting has been introduced as a compelling alternative to NeRF for Earth observation, offering com- petitive reconstruction quality with significantly reduced training times. In this work, we extend the Earth Observation Gaussian Splatting (EOGS) framework to propose EOGS++, a novel method tailored for satellite imagery that directly operates on raw high-resolution panchromatic data without requiring external preprocessing. Furthermore, leveraging optical flow techniques we embed bundle adjustment directly within the training process, avoiding reliance on external optimization tools while improving camera pose estimation. We also introduce several improvements to the original implementation, including early stopping and TSDF post-processing, all contributing to sharper reconstructions and better geometric accuracy. Experiments on the IARPA 2016 and DFC2019 datasets demonstrate that EOGS++ achieves state-of-the-art performance in terms of reconstruction quality and effi- ciency, outperforming the original EOGS method and other NeRF-based methods while maintaining the computational advantages of Gaussian Splatting. Our model demonstrates an improvement from 1.33 to 1.19 mean MAE errors on buildings compared to the original EOGS models

EOGS++ هو أسلوب جديد مقترح لمراقبة الأرض يعزز تقنية 3D Gaussian Splatting من خلال استخدام صور الأقمار الصناعية البانكروماتية عالية الدقة مباشرة. تلغي هذه الطريقة الحاجة إلى المعالجة المسبقة الخارجية وتدمج تقنيات تدفق الضوء لتحسين تقدير وضع الكاميرا. كما يقدم الأسلوب تحسينات مثل التوقف المبكر ومعالجة TSDF اللاحقة، مما يؤدي إلى إعادة بناء أكثر وضوحًا ودقة هندسية أفضل، كما يتضح من التجارب على مجموعات بيانات IARPA 2016 وDFC2019.

EOGS++ es un nuevo método propuesto para la observación de la Tierra que mejora el 3D Gaussian Splatting al utilizar directamente imágenes satelitales pancromáticas de alta resolución. Este enfoque elimina la necesidad de preprocesamiento externo e incorpora técnicas de flujo óptico para mejorar la estimación de la pose de la cámara. El método también presenta mejoras como la detención temprana y el post-procesamiento TSDF, lo que conduce a reconstrucciones más nítidas y una mejor precisión geométrica, como se demuestra en experimentos con los conjuntos de datos IARPA 2016 y DFC2019.

EOGS++ est une nouvelle méthode proposée pour l'observation de la Terre qui améliore le 3D Gaussian Splatting en utilisant directement des images satellites panchromatiques haute résolution brutes. Cette approche élimine le besoin de prétraitement externe et intègre des techniques de flux optique pour améliorer l'estimation de la pose de la caméra. La méthode comprend également des améliorations telles que l'arrêt précoce et le post-traitement TSDF, ce qui conduit à des reconstructions plus nettes et à une meilleure précision géométrique, comme le montrent les expériences sur les ensembles de …

EOGS++ is a newly proposed method for Earth observation that enhances 3D Gaussian Splatting by directly utilizing raw high-resolution panchromatic satellite imagery. This approach eliminates the need for external preprocessing and incorporates optical flow techniques for improved camera pose estimation. The method also features enhancements like early stopping and TSDF post-processing, leading to sharper reconstructions and better geometric accuracy, as demonstrated in experiments on the IARPA 2016 and DFC2019 datasets.

EOGS++: Earth Observation Gaussian Splatting with Internal Camera Refinement and Direct Panchromatic Rendering

arXiv:2511.18441v1 Announce Type: new 
Abstract: Gaussian Splatting has emerged as a leading method for novel view synthesis, offering superior training efficiency and real-time inference compared to NeRF approaches, while still delivering high-quality reconstructions. Beyond view synthesis, this 3D representation has also been explored for editing tasks. Many existing methods leverage 2D diffusion models to generate multi-view datasets for training, but they often suffer from limitations such as view inconsistencies, lack of fine-grained control, and high computational demand. In this work, we focus specifically on the editing task of recoloring. We introduce a user-friendly pipeline that enables precise selection and recoloring of regions within a pre-trained Gaussian Splatting scene. To demonstrate the real-time performance of our method, we also present an interactive tool that allows users to experiment with the pipeline in practice. Code is available at https://github.com/loryruta/recogs.

تم تقديم طريقة جديدة تسمى ReCoGS لإعادة تلوين المشاهد في الوقت الفعلي باستخدام Gaussian Splatting، المعروفة بكفاءتها في توليد وجهات نظر جديدة وإعادة بناء عالية الجودة. يسمح هذا النظام السهل الاستخدام بالاختيار الدقيق وإعادة تلوين المناطق داخل المشاهد المدربة مسبقًا، مما يظهر أداءً في الوقت الفعلي من خلال أداة تفاعلية. الكود الخاص بالطريقة متاح عبر الإنترنت.

Se ha introducido un nuevo método llamado ReCoGS para la recolorización en tiempo real de escenas utilizando Gaussian Splatting, reconocido por su eficiencia en la síntesis de nuevas vistas y reconstrucciones de alta calidad. Este pipeline fácil de usar permite la selección precisa y la recolorización de regiones dentro de escenas preentrenadas, demostrando un rendimiento en tiempo real a través de una herramienta interactiva. El código del método está disponible en línea.

Une nouvelle méthode appelée ReCoGS a été introduite pour le recolorisation en temps réel de scènes utilisant le Gaussian Splatting, reconnu pour son efficacité dans la synthèse de nouvelles vues et ses reconstructions de haute qualité. Ce pipeline convivial permet une sélection précise et une recolorisation de régions au sein de scènes pré-entraînées, démontrant des performances en temps réel grâce à un outil interactif. Le code de la méthode est disponible en ligne.

A new method called ReCoGS has been introduced for real-time recoloring of scenes using Gaussian Splatting, which is recognized for its efficiency in novel view synthesis and high-quality reconstructions. This user-friendly pipeline allows precise selection and recoloring of regions within pre-trained scenes, demonstrating real-time performance through an interactive tool. Code for the method is available online.

ReCoGS: Real-time ReColoring for Gaussian Splatting scenes

arXiv:2511.18806v1 Announce Type: new 
Abstract: X-ray imaging, based on penetration, enables detailed visualization of internal structures. Building on this capability, existing implicit 3D reconstruction methods have adapted the NeRF model and its variants for internal CT reconstruction. However, these approaches often neglect the significance of objects' anatomical priors for implicit learning, limiting both reconstruction precision and learning efficiency, particularly in ultra-sparse view scenarios. To address these challenges, we propose a novel 3D CT reconstruction framework that employs a 'target prior' derived from the object's projection data to enhance implicit learning. Our approach integrates positional and structural encoding to facilitate voxel-wise implicit reconstruction, utilizing the target prior to guide voxel sampling and enrich structural encoding. This dual strategy significantly boosts both learning efficiency and reconstruction quality. Additionally, we introduce a CUDA-based algorithm for rapid estimation of high-quality 3D target priors from sparse-view projections. Experiments utilizing projection data from a complex abdominal dataset demonstrate that the proposed model substantially enhances learning efficiency, outperforming the current leading model, NAF, by a factor of ten. In terms of reconstruction quality, it also exceeds the most accurate model, NeRP, achieving PSNR improvements of 3.57 dB, 5.42 dB, and 5.70 dB with 10, 20, and 30 projections, respectively. The code is available at https://github.com/qlcao171/TPG-INR.

تم تقديم إطار جديد يسمى TPG-INR لإعادة بناء التصوير المقطعي ثلاثي الأبعاد، مما يعزز التعلم الضمني من خلال استخدام 'مبدأ مستهدف' مستمد من بيانات الإسقاط. تهدف هذه الطريقة إلى تحسين دقة وكفاءة إعادة البناء، لا سيما في السيناريوهات ذات العرض النادر للغاية، من خلال دمج الترميز المكاني والهيكلي لإعادة البناء على مستوى الفوكسل.

Se ha introducido un nuevo marco llamado TPG-INR para la reconstrucción de CT 3D, que mejora el aprendizaje implícito al utilizar un 'prior objetivo' derivado de los datos de proyección. Este método busca mejorar la precisión y eficiencia de la reconstrucción, especialmente en escenarios de vista ultra-esparcida, integrando codificación posicional y estructural para la reconstrucción voxel por voxel.

Un nouveau cadre appelé TPG-INR a été introduit pour la reconstruction CT 3D, améliorant l'apprentissage implicite en utilisant un 'prior cible' dérivé des données de projection. Cette méthode vise à améliorer la précision et l'efficacité de la reconstruction, en particulier dans des scénarios de vue ultra-sparse, en intégrant un encodage positionnel et structurel pour la reconstruction voxel par voxel.

A novel framework called TPG-INR has been introduced for 3D CT reconstruction, enhancing implicit learning by utilizing a 'target prior' derived from projection data. This method aims to improve reconstruction precision and efficiency, particularly in ultra-sparse view scenarios, by integrating positional and structural encoding for voxel-wise reconstruction.

TPG-INR: Target Prior-Guided Implicit 3D CT Reconstruction for Enhanced Sparse-view Imaging

arXiv:2507.13861v4 Announce Type: replace 
Abstract: Recent subject-driven image customization excels in fidelity, yet fine-grained instance-level spatial control remains an elusive challenge, hindering real-world applications. This limitation stems from two factors: a scarcity of scalable, position-annotated datasets, and the entanglement of identity and layout by global attention mechanisms. To this end, we introduce \modelname{}, a unified framework for high-fidelity, spatially controllable multi-subject customization. First, we present BMPDS, the first automatic data-synthesis pipeline for position-annotated multi-subject datasets, effectively providing crucial spatial supervision. Second, we design a lightweight, layout-aware diffusion framework that integrates a novel visibility-aware attention mechanism. This mechanism explicitly models spatial relationships via an NeRF-inspired volumetric weight regulation to effectively decouple instance-level spatial embeddings from semantic identity features, enabling precise, occlusion-aware placement of multiple subjects.
  Extensive experiments demonstrate \modelname{} achieves state-of-the-art performance on public benchmarks, setting new records for spatial precision and identity consistency. Our work represents a significant step towards truly controllable, high-fidelity image customization in multi-entity scenarios. Code and data will be publicly released.

شهدت التطورات الأخيرة في تخصيص الصور تقديم PositionIC، وهو إطار مصمم لتحسين الدقة والتحكم المكاني في الصور متعددة الموضوعات. يتناول هذا التطور التحديات التي تطرحها ندرة مجموعات البيانات المعنونة بالموقع القابلة للتوسع وتعقيدات آليات الانتباه العالمية التي تربط الهوية والتخطيط. يتضمن PositionIC BMPDS، وهو خط أنابيب تلقائي لتوليد البيانات، وإطار نشر خفيف الوزن مدرك للتخطيط مع آلية انتباه جديدة مدركة للرؤية.

Los recientes avances en la personalización de imágenes han sido marcados por la introducción de PositionIC, un marco diseñado para mejorar la fidelidad y el control espacial en imágenes de múltiples sujetos. Este desarrollo aborda los desafíos planteados por la falta de conjuntos de datos anotados por posición a gran escala y las complejidades de los mecanismos de atención global que entrelazan identidad y diseño. PositionIC incorpora BMPDS, un pipeline de síntesis de datos automático, y un marco de difusión consciente del diseño con un nuevo mecanismo de atención consciente de la visibilidad…

Des avancées récentes dans la personnalisation d'images ont été marquées par l'introduction de PositionIC, un cadre conçu pour améliorer la fidélité et le contrôle spatial dans les images multi-sujets. Ce développement répond aux défis posés par le manque de jeux de données annotés par position à grande échelle et par les complexités des mécanismes d'attention globaux qui entremêlent identité et mise en page. PositionIC intègre BMPDS, un pipeline de synthèse de données automatique, et un cadre de diffusion conscient de la mise en page avec un nouveau mécanisme d'attention conscient de la visib…

Recent advancements in image customization have been marked by the introduction of PositionIC, a framework designed to enhance fidelity and spatial control in multi-subject images. This development addresses the challenges posed by the lack of scalable, position-annotated datasets and the complexities of global attention mechanisms that entangle identity and layout. PositionIC incorporates BMPDS, an automatic data-synthesis pipeline, and a layout-aware diffusion framework with a novel visibility-aware attention mechanism.

EOGS++: Earth Observation Gaussian Splatting with Internal Camera Refinement and Direct Panchromatic Rendering

Was this article worth reading? Share it

Aqaba.ai

OG Pilot

Ipgeolocation.io