arXiv:2510.21536v1 Announce Type: cross 
Abstract: Free space ground segmentation is essential to navigate robots and autonomous vehicles, recognize drivable zones, and traverse efficiently. Fine-grained features remain challenging for existing segmentation models, particularly for robots in indoor and structured environments. These difficulties arise from ineffective multi-scale processing, suboptimal boundary refinement, and limited feature representation. In order to overcome these limitations, we propose Attention-Guided Upsampling with Residual Boundary-Assistive Refinement (AURASeg), a ground-plane semantic segmentation model that maintains high segmentation accuracy while improving border precision. Our method uses CSP-Darknet backbone by adding a Residual Border Refinement Module (RBRM) for accurate edge delineation and an Attention Progressive Upsampling Decoder (APUD) for strong feature integration. We also incorporate a lightweight Atrous Spatial Pyramid Pooling (ASPP-Lite) module to ensure multi-scale context extraction without compromising real-time performance. The proposed model beats benchmark segmentation architectures in mIoU and F1 metrics when tested on the Ground Mobile Robot Perception (GMRP) Dataset and a custom Gazebo indoor dataset. Our approach achieves an improvement in mean Intersection-over-Union (mIoU) of +1.26% and segmentation precision of +1.65% compared to state-of-the-art models. These results show that our technique is feasible for autonomous perception in both indoor and outdoor environments, enabling precise border refinement with minimal effect on inference speed.

AURASeg هو نهج مبتكر لتحسين تقسيم الأرض للروبوتات والمركبات المستقلة، حيث يتناول التحديات الرئيسية في التعرف على المناطق القابلة للقيادة. من خلال تحسين المعالجة متعددة المقاييس وتنقيح الحدود، يعد هذا الأسلوب بزيادة كبيرة في كفاءة التنقل في البيئات المعقدة. هذه الخطوة مهمة لأنها تمهد الطريق لأنظمة مستقلة أكثر أمانًا وموثوقية، مما يجعلها تطورًا ملحوظًا في تكنولوجيا الروبوتات والذكاء الاصطناعي.

AURASeg es un enfoque innovador para mejorar la segmentación del suelo para robots y vehículos autónomos, abordando desafíos clave en el reconocimiento de áreas transitables. Al mejorar el procesamiento a múltiples escalas y refinar los límites, este método promete aumentar significativamente la eficiencia de navegación en entornos complejos. Este avance es crucial, ya que allana el camino para sistemas autónomos más seguros y confiables, convirtiéndolo en un desarrollo notable en la tecnología de robótica e IA.

AURASeg est une approche révolutionnaire pour améliorer la segmentation du sol pour les robots et les véhicules autonomes, répondant à des défis clés dans la reconnaissance des zones praticables. En améliorant le traitement multi-échelle et en affinant les frontières, cette méthode promet d'augmenter considérablement l'efficacité de la navigation dans des environnements complexes. Cette avancée est cruciale car elle ouvre la voie à des systèmes autonomes plus sûrs et plus fiables, ce qui en fait un développement remarquable dans la technologie de la robotique et de l'IA.

AURASeg is a groundbreaking approach to improving ground segmentation for robots and autonomous vehicles, addressing key challenges in recognizing drivable areas. By enhancing multi-scale processing and refining boundaries, this method promises to significantly boost navigation efficiency in complex environments. This advancement is crucial as it paves the way for safer and more reliable autonomous systems, making it a noteworthy development in robotics and AI technology.

AURASeg: Attention Guided Upsampling with Residual Boundary-Assistive Refinement for Drivable-Area Segmentation

Almost half of our attention during face-to-face conversation focuses on lip motion. Yet, robots still struggle to move their lips correctly. Even the most advanced humanoids make little more than muppet mouth gestures—if they have a face at all.

تعلم روبوت كيفية مزامنة الشفاه من خلال مشاهدة مقاطع الفيديو على يوتيوب، مما يعالج تحديًا كبيرًا في مجال الروبوتات حيث تكافح الروبوتات الشبيهة بالبشر غالبًا لتحريك شفاهها بشكل واقعي أثناء المحادثات. يسلط هذا التقدم الضوء على أهمية حركة الشفاه في التفاعل البشري، والتي تشكل ما يقرب من نصف الانتباه أثناء التواصل وجهًا لوجه.

Un robot ha aprendido a sincronizar los labios observando videos de YouTube, abordando un desafío significativo en la robótica donde los humanoides a menudo luchan por realizar movimientos realistas de los labios durante las conversaciones. Este avance destaca la importancia del movimiento de los labios en la interacción humana, que constituye casi la mitad de la atención durante la comunicación cara a cara.

Un robot a appris à synchroniser ses lèvres en observant des vidéos sur YouTube, ce qui répond à un défi majeur en robotique où les humanoïdes ont souvent du mal à reproduire des mouvements réalistes des lèvres lors des conversations. Cette avancée souligne l'importance du mouvement des lèvres dans l'interaction humaine, qui représente près de la moitié de l'attention lors des échanges en face à face.

A robot has learned to lip sync by observing YouTube videos, addressing a significant challenge in robotics where humanoids often struggle with realistic lip movements during conversations. This advancement highlights the importance of lip motion in human interaction, which constitutes nearly half of the attention during face-to-face communication.

Robot learns to lip sync by watching YouTube

arXiv:2601.06874v2 Announce Type: replace 
Abstract: Most existing 3D referring expression segmentation (3DRES) methods rely on dense, high-quality point clouds, while real-world agents such as robots and mobile phones operate with only a few sparse RGB views and strict latency constraints. We introduce Multi-view 3D Referring Expression Segmentation (MV-3DRES), where the model must recover scene structure and segment the referred object directly from sparse multi-view images. Traditional two-stage pipelines, which first reconstruct a point cloud and then perform segmentation, often yield low-quality geometry, produce coarse or degraded target regions, and run slowly. We propose the Multimodal Visual Geometry Grounded Transformer (MVGGT), an efficient end-to-end framework that integrates language information into sparse-view geometric reasoning through a dual-branch design. Training in this setting exposes a critical optimization barrier, termed Foreground Gradient Dilution (FGD), where sparse 3D signals lead to weak supervision. To resolve this, we introduce Per-view No-target Suppression Optimization (PVSO), which provides stronger and more balanced gradients across views, enabling stable and efficient learning. To support consistent evaluation, we build MVRefer, a benchmark that defines standardized settings and metrics for MV-3DRES. Experiments show that MVGGT establishes the first strong baseline and achieves both high accuracy and fast inference, outperforming existing alternatives. Code and models are publicly available at https://mvggt.github.io.

تم تقديم المحول متعدد الوسائط للجيوميتري البصرية (MVGGT) كإطار جديد لتجزئة التعبير المرجعي ثلاثي الأبعاد متعدد المناظر (MV-3DRES)، حيث يعالج القيود المفروضة على الأساليب الحالية التي تعتمد على سحب النقاط الكثيفة. يسمح MVGGT بالتجزئة مباشرة من الصور متعددة المناظر النادرة، مما يعزز الكفاءة والأداء في التطبيقات الواقعية.

Se ha presentado el Transformador Multimodal de Geometría Visual (MVGGT) como un nuevo marco para la Segmentación de Expresión Referencial 3D Multivista (MV-3DRES), abordando las limitaciones de los métodos existentes que dependen de nubes de puntos densas. MVGGT permite la segmentación directamente a partir de imágenes multivista escasas, mejorando la eficiencia y el rendimiento en aplicaciones del mundo real.

Le Transformateur Multimodal de Géométrie Visuelle (MVGGT) a été introduit comme un cadre novateur pour la Segmentation d'Expression Référentielle 3D Multivue (MV-3DRES), répondant aux limitations des méthodes existantes qui dépendent de nuages de points denses. MVGGT permet la segmentation directement à partir d'images multivues éparses, améliorant l'efficacité et la performance dans des applications réelles.

The Multimodal Visual Geometry Grounded Transformer (MVGGT) has been introduced as a novel framework for Multiview 3D Referring Expression Segmentation (MV-3DRES), addressing the limitations of existing methods that depend on dense point clouds. MVGGT enables segmentation directly from sparse multi-view images, enhancing efficiency and performance in real-world applications.

MVGGT: Multimodal Visual Geometry Grounded Transformer for Multiview 3D Referring Expression Segmentation

One More Thing in AI – Your Shortcut to AI Mastery

AURASeg: Attention Guided Upsampling with Residual Boundary-Assistive Refinement for Drivable-Area Segmentation

Was this article worth reading? Share it

One More Thing in AI

LucidQuery AI

Attentive AI

Aqaba.ai

Dyad

AIPortalX

Ready to build your own newsroom?