arXiv subjects

Yakun Huang

Publications and source records attributed to Yakun Huang.

9 recordsLinked to original sources

arXiv2026

AOMGen: Photoreal, Physics-Consistent Demonstration Generation for Articulated Object Manipulation

Recent advances in Vision-Language-Action (VLA) and world-model methods have improved generalization in tasks such as robotic manipulation and object interaction. However, Successful execution of such tasks depends on large, costly collections of real demonstrations, especially for fine-grained manipulation of articulated objects. To address this, we present AOMGen, a scalable data generation framework for articulated manipulation which is instantiated from a single real scan, demonstration and a library of readily available digital assets, yielding photoreal training data with verified physical states. The framework synthesizes synchronized multi-view RGB temporally aligned with action commands and state annotations for joints and contacts, and systematically varies camera viewpoints, object styles, and object poses to expand a single execution into a diverse corpus. Experimental results demonstrate that fine-tuning VLA policies on AOMGen data increases the success rate from 0% to 88.7%, and the policies are tested on unseen objects and layouts.

cs.RO↗

arXiv2026

PD$^{2}$GS: Part-Level Decoupling and Continuous Deformation of Articulated Objects via Gaussian Splatting

Articulated objects are ubiquitous and important in robotics, AR/VR, and digital twins. Most self-supervised methods for articulated object modeling reconstruct discrete interaction states and relate them via cross-state geometric consistency, yielding representational fragmentation and drift that hinder smooth control of articulated configurations. We introduce PD$^{2}$GS, a novel framework that learns a shared canonical Gaussian field and models the arbitrary interaction state as its continuous deformation, jointly encoding geometry and kinematics. By associating each interaction state with a latent code and refining part boundaries using generic vision priors, PD$^{2}$GS enables accurate and reliable part-level decoupling while enforcing mutual exclusivity between parts and preserving scene-level coherence. This unified formulation supports part-aware reconstruction, fine-grained continuous control, and accurate kinematic modeling, all without manual supervision. To assess realism and generalization, we release RS-Art, a real-to-sim RGB-D dataset aligned with reverse-engineered 3D models, supporting real-world evaluation. Extensive experiments demonstrate that PD$^{2}$GS surpasses prior methods in geometric and kinematic accuracy, and in consistency under continuous control, both on synthetic and real data.

cs.CV↗

arXiv2025

ArtGen: Conditional Generative Modeling of Articulated Objects in Arbitrary Part-Level States

Generating articulated assets is crucial for robotics, digital twins, and embodied intelligence. Existing generative models often rely on single-view inputs representing closed states, resulting in ambiguous or unrealistic kinematic structures due to the entanglement between geometric shape and joint dynamics. To address these challenges, we introduce ArtGen, a conditional diffusion-based framework capable of generating articulated 3D objects with accurate geometry and coherent kinematics from single-view images or text descriptions at arbitrary part-level states. Specifically, ArtGen employs cross-state Monte Carlo sampling to explicitly enforce global kinematic consistency, reducing structural-motion entanglement. Additionally, we integrate a Chain-of-Thought reasoning module to infer robust structural priors, such as part semantics, joint types, and connectivity, guiding a sparse-expert Diffusion Transformer to specialize in diverse kinematic interactions. Furthermore, a compositional 3D-VAE latent prior enhanced with local-global attention effectively captures fine-grained geometry and global part-level relationships. Extensive experiments on the PartNet-Mobility benchmark demonstrate that ArtGen significantly outperforms state-of-the-art methods.

cs.CV↗

arXiv2024

SM$^3$: Self-Supervised Multi-task Modeling with Multi-view 2D Images for Articulated Objects

Reconstructing real-world objects and estimating their movable joint structures are pivotal technologies within the field of robotics. Previous research has predominantly focused on supervised approaches, relying on extensively annotated datasets to model articulated objects within limited categories. However, this approach falls short of effectively addressing the diversity present in the real world. To tackle this issue, we propose a self-supervised interaction perception method, referred to as SM$^3$, which leverages multi-view RGB images captured before and after interaction to model articulated objects, identify the movable parts, and infer the parameters of their rotating joints. By constructing 3D geometries and textures from the captured 2D images, SM$^3$ achieves integrated optimization of movable part and joint parameters during the reconstruction process, obviating the need for annotations. Furthermore, we introduce the MMArt dataset, an extension of PartNet-Mobility, encompassing multi-view and multi-modal data of articulated objects spanning diverse categories. Evaluations demonstrate that SM$^3$ surpasses existing benchmarks across various categories and objects, while its adaptability in real-world scenarios has been thoroughly validated.

cs.CV↗

arXiv2023

DTF-Net: Category-Level Pose Estimation and Shape Reconstruction via Deformable Template Field

Estimating 6D poses and reconstructing 3D shapes of objects in open-world scenes from RGB-depth image pairs is challenging. Many existing methods rely on learning geometric features that correspond to specific templates while disregarding shape variations and pose differences among objects in the same category. As a result, these methods underperform when handling unseen object instances in complex environments. In contrast, other approaches aim to achieve category-level estimation and reconstruction by leveraging normalized geometric structure priors, but the static prior-based reconstruction struggles with substantial intra-class variations. To solve these problems, we propose the DTF-Net, a novel framework for pose estimation and shape reconstruction based on implicit neural fields of object categories. In DTF-Net, we design a deformable template field to represent the general category-wise shape latent features and intra-category geometric deformation features. The field establishes continuous shape correspondences, deforming the category template into arbitrary observed instances to accomplish shape reconstruction. We introduce a pose regression module that shares the deformation features and template codes from the fields to estimate the accurate 6D pose of each object in the scene. We integrate a multi-modal representation extraction module to extract object features and semantic masks, enabling end-to-end inference. Moreover, during training, we implement a shape-invariant training strategy and a viewpoint sampling method to further enhance the model's capability to extract object pose features. Extensive experiments on the REAL275 and CAMERA25 datasets demonstrate the superiority of DTF-Net in both synthetic and real scenes. Furthermore, we show that DTF-Net effectively supports grasping tasks with a real robot arm.

cs.CV↗

arXiv2023

Building a Modal-balanced BlockChain with Semantic Reconstruction

The current large blockchain systems (BTC Lightning network, Ethereum, etc.) are generally facing the problems of low persistence rates and high storage costs. Therefore, users tend to store single modal (textual) information on the existing blockchain systems. Inspired by semantic communication algorithms, this paper presents a new algorithm to solve the serious imbalance between textual and visual modals on blockchains. After semantic sampling of the original visual image, the resulting semantic text will be stored on the chain, and the end users can reconstruct a semantically similar image using the \textbf{R}elative \textbf{O}ptimal \textbf{S}emantic \textbf{I}sotope \textbf{S}election algorithm. Experiments on the DIV2K dataset show that the blockchain with our algorithm can achieve 430,000 times the storage capacity and 550,000 times the persistence rate for the original visual data with acceptable semantic information loss.

cs.MM↗

arXiv2022

Towards Holographic Video Communications: A Promising AI-driven Solution

Real-time holographic video communications enable immersive experiences for next-generation video services in the future metaverse era. However, high-fidelity holographic videos require high bandwidth and significant computation resources, which exceed the transferring and computing capacity of 5G networks. This article reviews state-of-the-art holographic point cloud video (PCV) transmission techniques and highlights the critical challenges of delivering such immersive services. We further implement a preliminary prototype of an AI-driven holographic video communication system and present critical experimental results to evaluate its performance. Finally, we identify future research directions and discuss potential solutions for providing real-time and high-quality holographic experiences.

cs.MM↗

arXiv2022

Multi-Player Immersive Communications and Interactions in Metaverse: Challenges, Architecture, and Future Directions

The metaverse has awakened users' expectations of an immersive interaction that fuses the virtual digital world and the physical world across space and time. However, the metaverse is still in its infancy, typically expanding multi-player applications (e.g., multi-player games) to implement a prototype with the help of 5G/Beyond 5G, Artificial Intelligence, digital twin, and other enabling technologies. This article reviews the characteristics, key enabling technologies, and driving applications of the state-of-the-art metaverse. We focus on the immersive interactions perspective of the metaverse from the tasks, inputs, and feedback across the users, digital world, and physical world and reveal the key challenges. Afterwards, we present a multi-player interaction prototype platform based on a cloud-edge-device collaborative framework. Also, we evaluate it with centralized and device-to-device (D2D) approaches to verify the efficiency and flexibility of interactions. Finally, we point out future research approaches and discuss potential solutions to enable more stable and higher quality multi-player interactions for metaverse services.

cs.MM↗

arXiv2022

ISCom: Interest-aware Semantic Communication Scheme for Point Cloud Video Streaming

The provisioning of immersive point cloud video (PCV) streaming on pervasive mobile devices is a cornerstone for enabling immersive communication and interactions in the future 6G metaverse era. However, most streaming techniques are dedicated to efficient PCV compression and codec extending from traditional 3-DoF video services. Some emerging AI-enabled approaches are still in their infancy phase and are constrained by intensive computational and adaptive flow techniques. In this paper, we present ISCom, an Interest-aware Semantic Communication Scheme for PCV, consisting of a region-of-interest (ROI) selection module, a lightweight PCV streaming module, and an intelligent scheduler. First, we propose a two-stage efficient ROI selection method for providing interest-aware PCV streaming, which significantly reduces the data volume. Second, we design a lightweight PCV encoder-decoder network for resource-constrained devices, adapting to the heterogeneous computing capabilities of terminals. Third, we train a deep reinforcement learning (DRL)-based scheduler to adapt an optimal encoder-decoder network for various devices, considering the dynamic network environments and computing capabilities of different devices. Extensive experiments show that ISCom outperforms baselines on mobile devices at least 10 FPS and up to 22 FPS.

cs.MM↗