arXiv:2506.01802v2 Announce Type: replace 
Abstract: Learning an animatable and clothed human avatar model with vivid dynamics and photorealistic appearance from multi-view videos is an important foundational research problem in computer graphics and vision. Fueled by recent advances in implicit representations, the quality of the animatable avatars has achieved an unprecedented level by attaching the implicit representation to drivable human template meshes. However, they usually fail to preserve the highest level of detail, particularly apparent when the virtual camera is zoomed in and when rendering at 4K resolution and higher. We argue that this limitation stems from inaccurate surface tracking, specifically, depth misalignment and surface drift between character geometry and the ground truth surface, which forces the detailed appearance model to compensate for geometric errors. To address this, we propose a latent deformation model and supervising the 3D deformation of the animatable character using guidance from foundational 2D video point trackers, which offer improved robustness to shading and surface variations, and are less prone to local minima than differentiable rendering. To mitigate the drift over time and lack of 3D awareness of 2D point trackers, we introduce a cascaded training strategy that generates consistent 3D point tracks by anchoring point tracks to the rendered avatar, which ultimately supervises our avatar at the vertex and texel level. To validate the effectiveness of our approach, we introduce a novel dataset comprising five multi-view video sequences, each over 10 minutes in duration, captured using 40 calibrated 6K-resolution cameras, featuring subjects dressed in clothing with challenging texture patterns and wrinkle deformations. Our approach demonstrates significantly improved performance in rendering quality and geometric accuracy over the prior state of the art.

تقدم دراسة حديثة UMA، وهو نهج مبتكر لإنشاء صور رمزية بشرية فائقة التفاصيل من خلال محاذاة الأسطح متعددة المستويات. تتيح هذه التطورات في الرسوميات الحاسوبية والرؤية إنشاء صور رمزية قابلة للتحريك لا تبدو فقط واقعية بشكل مذهل، بل تظهر أيضًا حركات ديناميكية. من خلال الاستفادة من التمثيلات الضمنية، تمكن الباحثون من تحسين جودة هذه الصور الرمزية بشكل كبير، مما يجعلها أكثر واقعية من أي وقت مضى. هذه الابتكارات مهمة لأنها تفتح آفاقًا جديدة للتطبيقات في الألعاب، والواقع الافتراضي، وإنشاء المحتوى الرقمي، مما يعزز تجارب وتفاعلات المستخدمين.

Un estudio reciente presenta UMA, un enfoque innovador para crear avatares humanos ultra-detallados mediante la alineación de superficies en múltiples niveles. Este avance en gráficos por computadora y visión permite avatares animables que no solo lucen fotorealistas, sino que también exhiben movimientos dinámicos. Al aprovechar representaciones implícitas, los investigadores han mejorado significativamente la calidad de estos avatares, haciéndolos más realistas que nunca. Esta innovación es crucial, ya que abre nuevas posibilidades para aplicaciones en juegos, realidad virtual y creación de contenido digital, mejorando las experiencias e interacciones de los usuarios.

Une étude récente présente UMA, une approche révolutionnaire pour créer des avatars humains ultra-détaillés grâce à l'alignement de surfaces multi-niveaux. Cette avancée dans les graphiques informatiques et la vision permet de créer des avatars animables qui non seulement ont un aspect photoréaliste, mais montrent également des mouvements dynamiques. En s'appuyant sur des représentations implicites, les chercheurs ont considérablement amélioré la qualité de ces avatars, les rendant plus réalistes que jamais. Cette innovation est cruciale car elle ouvre de nouvelles voies pour des applications dans les jeux, la réalité virtuelle et la création de contenu numérique, améliorant ainsi les expériences et interactions des utilisateurs.

A recent study introduces UMA, a groundbreaking approach to creating ultra-detailed human avatars using multi-level surface alignment. This advancement in computer graphics and vision allows for animatable avatars that not only look photorealistic but also exhibit dynamic movements. By leveraging implicit representations, researchers have significantly improved the quality of these avatars, making them more lifelike than ever. This innovation is crucial as it opens new avenues for applications in gaming, virtual reality, and digital content creation, enhancing user experiences and interactions.

UMA: Ultra-detailed Human Avatars via Multi-level Surface Alignment

arXiv:2506.01579v2 Announce Type: replace 
Abstract: Generating high-fidelity full-body human interactions with dynamic objects and static scenes remains a critical challenge in computer graphics and animation. Existing methods for human-object interaction often neglect scene context, leading to implausible penetrations, while human-scene interaction approaches struggle to coordinate fine-grained manipulations with long-range navigation. To address these limitations, we propose HOSIG, a novel framework for synthesizing full-body interactions through hierarchical scene perception. Our method decouples the task into three key components: 1) a scene-aware grasp pose generator that ensures collision-free whole-body postures with precise hand-object contact by integrating local geometry constraints, 2) a heuristic navigation algorithm that autonomously plans obstacle-avoiding paths in complex indoor environments via compressed 2D floor maps and dual-component spatial reasoning, and 3) a scene-guided motion diffusion model that generates trajectory-controlled, full-body motions with finger-level accuracy by incorporating spatial anchors and dual-space classifier-free guidance. Extensive experiments on the TRUMANS dataset demonstrate superior performance over state-of-the-art methods. Notably, our framework supports unlimited motion length through autoregressive generation and requires minimal manual intervention. This work bridges the critical gap between scene-aware navigation and dexterous object manipulation, advancing the frontier of embodied interaction synthesis. Codes will be available after publication. Project page: http://yw0208.github.io/hosig

تم تقديم HOSIG، وهو إطار جديد لتوليد تفاعلات بشرية كاملة الجسم مع كائنات ديناميكية ومشاهد ثابتة، مما يعالج تحديات كبيرة في الرسوميات الحاسوبية والرسوم المتحركة. من خلال استخدام الإدراك الهرمي للمشهد، يعزز HOSIG واقعية التفاعلات بين الإنسان والكائن، مع ضمان أوضاع خالية من الاصطدام وتخطيط فعال في البيئات المعقدة.

La introducción de HOSIG, un nuevo marco para generar interacciones humanas de cuerpo completo con objetos dinámicos y escenas estáticas, aborda desafíos significativos en gráficos por computadora y animación. Al utilizar la percepción jerárquica de la escena, HOSIG mejora el realismo de las interacciones humano-objeto, asegurando posturas libres de colisiones y una navegación efectiva en entornos complejos.

L'introduction de HOSIG, un nouveau cadre pour générer des interactions humaines à corps entier avec des objets dynamiques et des scènes statiques, répond à des défis significatifs dans les graphismes informatiques et l'animation. En utilisant une perception hiérarchique de la scène, HOSIG améliore le réalisme des interactions humain-objet tout en garantissant des postures sans collision et une navigation efficace dans des environnements complexes.

The introduction of HOSIG, a novel framework for generating full-body human interactions with dynamic objects and static scenes, addresses significant challenges in computer graphics and animation. By utilizing hierarchical scene perception, HOSIG enhances the realism of human-object interactions while ensuring collision-free postures and effective navigation in complex environments.

HOSIG: Full-Body Human-Object-Scene Interaction Generation with Hierarchical Scene Perception

arXiv:2511.18005v1 Announce Type: new 
Abstract: City-scale 3D generation is of great importance for the development of embodied intelligence and world models. Existing methods, however, face significant challenges regarding quality, fidelity, and scalability in 3D world generation. Thus, we propose RAISECity, a \textbf{R}eality-\textbf{A}ligned \textbf{I}ntelligent \textbf{S}ynthesis \textbf{E}ngine that creates detailed, \textbf{C}ity-scale 3D worlds. We introduce an agentic framework that leverages diverse multimodal foundation tools to acquire real-world knowledge, maintain robust intermediate representations, and construct complex 3D scenes. This agentic design, featuring dynamic data processing, iterative self-reflection and refinement, and the invocation of advanced multimodal tools, minimizes cumulative errors and enhances overall performance. Extensive quantitative experiments and qualitative analyses validate the superior performance of RAISECity in real-world alignment, shape precision, texture fidelity, and aesthetics level, achieving over a 90% win-rate against existing baselines for overall perceptual quality. This combination of 3D quality, reality alignment, scalability, and seamless compatibility with computer graphics pipelines makes RAISECity a promising foundation for applications in immersive media, embodied intelligence, and world models.

تم تقديم RAISECity كإطار عمل متعدد الوسائط مصمم لتحسين إنشاء العوالم ثلاثية الأبعاد على نطاق المدينة، حيث يتناول التحديات المتعلقة بالجودة والموثوقية وقابلية التوسع التي تواجهها الأساليب الحالية. يستخدم هذا الإطار أدوات متعددة الوسائط متنوعة لإنشاء بيئات ثلاثية الأبعاد مفصلة، بهدف تحسين الذكاء المجسد ونماذج العالم.

RAISECity se ha presentado como un marco de agente multimodal diseñado para mejorar la generación de mundos 3D a escala de ciudad, abordando los desafíos de calidad, fidelidad y escalabilidad que enfrentan los métodos actuales. Este marco utiliza diversas herramientas de fundación multimodal para crear entornos 3D detallados, con el objetivo de mejorar la inteligencia encarnada y los modelos del mundo.

RAISECity a été présenté comme un cadre d'agent multimodal conçu pour améliorer la génération de mondes 3D à l'échelle de la ville, en répondant aux défis de qualité, de fidélité et d'évolutivité auxquels les méthodes actuelles sont confrontées. Ce cadre utilise divers outils de fondation multimodaux pour créer des environnements 3D détaillés, visant à améliorer l'intelligence incarnée et les modèles du monde.

RAISECity has been introduced as a multimodal agent framework designed to enhance city-scale 3D world generation, addressing challenges in quality, fidelity, and scalability that current methods face. This framework utilizes diverse multimodal foundation tools to create detailed 3D environments, aiming to improve embodied intelligence and world models.

UMA: Ultra-detailed Human Avatars via Multi-level Surface Alignment

Was this article worth reading? Share it

SwapAnything.io

Aitryon-art

VidBoard AI