Intelligent digital humans have rapidly evolved with the advancement of computer graphics,computer vision,speech synthesis,and multimodal generative modeling.From early virtual avatars that focus on visual representation,digi-tal humans are currently developing toward dynamic motion modeling,emotion-aware interaction,and real-time deploy-ment.This study presents a systematic review of recent research progress in intelligent digital human content generation,organized around three core technical directions:video-to-digital human generation,3D human motion synthesis and edit-ing,and emotion-driven digital human generation.In addition,practical considerations for real-time on-device deployment are discussed.Video-to-digital human generation serves as the foundational stage for digital human construction.Its objec-tive is to reconstruct animatable 3D human avatars from monocular,multi-view,or in-the-wild video input.Early approaches primarily relied on implicit neural representations,such as neural radiance fields,frequently combined with parametric body models,such as the skinned multi-person linear model(SMPL).Although implicit methods provide con-tinuous and high-fidelity geometric representation,their rendering efficiency limits real-time applicability.Recent studies have shifted toward explicit or hybrid representations,particularly 3D Gaussian splatting,which significantly improves ren-dering speed while maintaining visual quality.Extensions that incorporate SMPL or SMPL-X priors further enhance geomet-ric stability and animatability.In multi-view settings,stronger geometric constraints improve reconstruction accuracy,while open-scene scenarios introduce additional challenges,such as occlusion handling,multi-person interaction,and background interference.Despite notable progress,maintaining temporal consistency and geometric robustness in complex environments remains an open problem.In addition to geometric reconstruction,3D human motion synthesis and editing enable digital humans to exhibit realistic dynamic behaviors.Compared with static modeling,motion generation requires accurate modeling of high-dimensional temporal distributions under kinematic and physical constraints.Early approaches based on statistical models or variational autoencoders improved representation capacity but frequently suffered from limited motion diversity.In recent years,diffusion models have become the dominant paradigm for motion generation due to their strong capability to model complex multimodal distributions.Representative frameworks demonstrate improved motion real-ism,diversity,and semantic alignment with textual or conditional input.Latent diffusion strategies further enhance effi-ciency by performing denoising processes in compact latent spaces.Beyond unconditional generation,condition-driven and fine-grained motion editing have attracted increasing attention.Text-guided editing frameworks allow local modification of specific joints or temporal segments while preserving overall motion style.Skeleton-aware and physics-guided diffusion models introduce structural constraints to improve anatomical plausibility and reduce artifacts,such as foot sliding.More-over,research has gradually expanded toward multi-person interaction modeling and long-sequence coherence,addressing challenges in action composition,interaction synchronization,and environment-aware motion planning.Nevertheless,bal-ancing physical consistency,computational efficiency,and controllability remains a critical challenge in practical applica-tions.Emotion-driven digital human generation further enhances interactivity and human-likeness.This direction includes facial expression synthesis,emotional speech synthesis,and multi-turn empathetic interaction modeling.In facial anima-tion,research has progressed from parameterized 3D morphable models to implicit neural rendering and,more recently,Gaussian-based explicit representations that achieve improved fidelity and real-time performance.In emotional speech syn-thesis,end-to-end neural architectures,non-autoregressive frameworks,and neural codec language models enable expres-sive,zero-shot,and fine-grained controllable speech generation.Meanwhile,emotion modeling in interactive dialogue sys-tems has evolved from passive emotion recognition toward empathetic response generation,incorporating graph-based con-textual modeling and large language model fine-tuning strategies.Although current systems can generate recognizable emo-tional expressions,challenges remain in maintaining emotional consistency over long interactions,decoupling emotion from underlying controllable factors,and ensuring cross-modal alignment in the speech,facial motion,and semantic contexts.To support real-world deployment,real-time on-device digital human systems have also gained attention.Lightweight mod-els,reduced-resolution rendering,intermediate parameter representations,and efficient inference frameworks are com-monly adopted under constrained computational resources.In practical applications,a collaborative architecture is fre-quently employed,where large language models handle semantic reasoning in the cloud while speech synthesis and avatar rendering are executed locally.This edge-cloud collaboration balances interaction latency and generation quality,facilitat-ing scalable deployment in mobile and desktop environments.In addition to reviewing representative models and technical routes,this work summarizes commonly used datasets and evaluation metrics across subfields,including text-to-motion benchmarks,emotional speech corpora,and multi-view reconstruction datasets.Performance is typically evaluated from multiple perspectives,such as perceptual realism,geometric accuracy,semantic alignment,motion stability,and subjec-tive human assessment.To facilitate reproducible research and provide a centralized resource for the community,we have curated all surveyed datasets,benchmark links,and a structured list of representative models into a public GitHub reposi-tory,which is available at: rapid prog-ress,unified benchmarks for long-term interactive digital humans are still lacking.Overall,intelligent digital human tech-nology is advancing along a progressive pathway from geometric reconstruction to motion generation,and finally,emotion-aware interaction.Future research is expected to focus on unified multimodal generative frameworks,improved long-term consistency modeling,physics-aware motion control,and efficient real-time deployment.By systematically organizing recent developments and open challenges,this review aims to provide a structured understanding of current progress and potential research directions in intelligent digital human content generation.

Image appearance transfer plays a significant role in interior design by allowing designers to efficiently explore different design styles according to clients' preferences. Given as input an example image and a target scene, the goal is to efficiently produce scene images that exhibit the desired appearance while maintaining the harmonization of the entire scene. For interior designs composed of multiple objects, the key to object-aware appearance transfer is to prevent scrappy appearance features from being distributed all over the generated images. In this paper, we utilize a pre-trained vision�language model (VLM) and a text-to-image generative model to solve the object-aware appearance transfer task. Specifically, we propose a VLM-assisted align-and-complement strategy using scene graph representation to determine object appearance with comprehensive considerations in the target scene. In addition, when conducting multi-object appearance transfer, we propose a multiple contrastive loss to learn object-aware appearance features from single examples and to manipulate the compositional conditions to precisely control the transfer. We have constructed an evaluation dataset and performed comparative experiments to demonstrate the effectiveness of our method of object-aware appearance transfer for interior designs. Both qualitative and quantitative evaluations demonstrate that our method successfully transfers object appearances from an example image to target scenes without feature leakage, achieving superior visual effects to competing solutions.

Reconstructing articulated objects into high-fidelity digital twins is crucial for applications such as robotic manipulation and interactive simulation. Recent self-supervised methods using differentiable rendering frameworks like 3D Gaussian Splatting remain highly sensitive to the initial part segmentation. Their reliance on heuristic clustering or pre-trained models often causes optimization to converge to local minima, especially for complex multi-part objects. To address these limitations, we propose ArtPro, a novel self-supervised framework that introduces adaptive integration of mobility proposals. Our approach begins with an over-segmentation initialization guided by geometry features and motion priors, generating part proposals with plausible motion hypotheses. During optimization, we dynamically merge these proposals by analyzing motion consistency among spatial neighbors, while a collision-aware motion pruning mechanism prevents erroneous kinematic estimation. Extensive experiments on both synthetic and real-world objects demonstrate that ArtPro achieves robust reconstruction of complex multi-part objects, significantly outperforming existing methods in accuracy and stability.

Mobile manipulation is a key capability for embodied intelligence, enabling robots to accomplish complex multi-stage tasks in open-world environments. However, mobile manipulation poses two key challenges for vision-language-action (VLA) policies: At the data level, the efficient collection of high-quality whole-body demonstrations demands the coordinated control of both the mobile base and the robotic arms; at the model level, existing VLA models predominantly rely on local camera observations, whose limited field of view hinders global spatial understanding. To address these challenges, we develop a whole-body teleoperation system and a panoramic-aware VLA policy. The system enables coordinated control of a wheeled bimanual robot through a single VR interface and supports the acquisition of a real-world mobile manipulation dataset comprising 5.5 hours of multimodal demonstrations. Building upon this dataset, we propose PanoVLA, a panorama-aware vision-language-action policy for mobile bimanual manipulation. Built upon a Mixture-of-Transformers architecture, PanoVLA introduces global spatial context through dedicated panorama encoding and fusion modules, enabling effective integration of panoramic observations with language instructions and robot states for action generation. Evaluation on four real-world mobile manipulation tasks demonstrates that PanoVLA achieves an average stage completion rate of 91.3% and an end-to-end success rate of 73.4%, substantially outperforming local-view baselines. These results demonstrate that incorporating panoramic spatial context improves spatial understanding and closed-loop manipulation performance in mobile robots.

Recovering a continuous colormap from a single 2D scalar field visualization can be quite challenging, especially in the absence of a corresponding color legend. In this paper, we propose a novel colormap recovery approach that extracts the colormap from a color-encoded 2D scalar field visualization by simultaneously predicting the colormap and underlying data using a decoupling-and-reconstruction strategy. Our approach first separates the input visualization into colormap and data using a decoupling module, then reconstructs the visualization with a differentiable color-mapping module. To guide this process, we design a reconstruction loss between the input and reconstructed visualizations, which serves both as a constraint to ensure strong correlation between colormap and data during training, and as a self-supervised optimizer for fine-tuning the predicted colormap of unseen visualizations during inferencing. To ensure smoothness and correct color ordering in the extracted colormap, we introduce a compact colormap representation using cubic B-spline curves and an associated color order loss. We evaluate our method quantitatively and qualitatively on a synthetic dataset and a collection of real-world visualizations from the VIS30K dataset [9]. Additionally, we demonstrate its utility in two prototype applications-colormap adjustment and colormap transfer-and explore its generalization to visualizations with color legends and ones encoded using discrete color palettes.

The rapid growth of Artificial Intelligence-generated content (AIGC) is reshaping video production and circulation, exposing children to an increasing volume of AIGC videos. Unlike traditionally produced videos, AIGC videos often exhibit greater uncertainty in visual details, narrative coherence, and content expression, which may introduce developmentally inappropriate risks for children. However, existing video safety research is largely designed for general violation detection from an adult perspective and remains insufficient for identifying the fine-grained, implicit, and context-dependent risks that children may encounter when viewing AIGC videos. To address this gap, we study child-oriented AIGC video reviewing, making three contributions. First, we construct CAVSR, a benchmark of 605 real-world videos collected from multiple platforms, and develop a hierarchical risk taxonomy comprising 6 top-level categories and 26 fine-grained labels to support systematic evaluation of children's viewing risks. Second, we propose QVRS-E, a knowledge- and experience-augmented video reviewing framework that combines multi-agent collaboration with expert and experiential knowledge to support targeted evidence acquisition and fact-grounded reviewing decisions. Third, extensive experiments demonstrate that our method significantly enhances the reviewing of child-related risks integrated with vision-language models, and yields more robust review reports.

Controllability plays a crucial role in the practical applications of 3D indoor scene synthesis. Existing works either allow rough language-based control, that is convenient but lacks fine-grained scene customization, or employ graph based control, which offers better controllability but demands considerable knowledge for the cumbersome graph design process. To address these challenges, we present FreeScene, a user-friendly framework that enables both convenient and effective control for indoor scene synthesis.Specifically, FreeScene supports free-form user inputs including text description and/or reference images, allowing users to express versatile design intentions. The user inputs are adequately analyzed and integrated into a graph representation by a VLM-based Graph Designer. We then propose MG-DiT, a Mixed Graph Diffusion Transformer, which performs graph-aware denoising to enhance scene generation. Our MG-DiT not only excels at preserving graph structure but also offers broad applicability to various tasks, including, but not limited to, text-to-scene, graph-to-scene, and rearrangement, all within a single model. Extensive experiments demonstrate that FreeScene provides an efficient and user-friendly solution that unifies text-based and graph based scene synthesis, outperforming state-of-the-art methods in terms of both generation quality and controllability in a range of applications.

Story visualization aims to create a series of visually consistent images from written stories. With the advancement of large models, visualization techniques have progressed from generating characters limited to predefined datasets to creating open-ended story. Although these techniques have achieved impressive results, several challenges still need to be addressed. For example, maintaining character consistency in scenes with multiple characters and transforming story text into usable information for accurate image generation remain significant challenges. To address these challenges, We propose StoryWeaver, a framework designed for consistent, multi-character, and open-ended story generation. StoryWeaver incorporates trainable prompt templates, allowing the large language model to effectively decompose the story text into the required number of images and corresponding prompts, character descriptions, and story captions for each image. This process ensures that the key elements of the story are accurately translated into visual content. During image generation, we propose a method to ensure character consistency, especially in multi-character scenes. This is achieved by extracting image embeddings from the self-attention layers and converting character prompts into text embeddings using a tokenizer. These embeddings are injected into the target image generation process and applied to both the selfattention and cross-attention layers in a region-specific manner. This approach ensures consistency across characters and prevents interference between them. Users can incorporate pose images or other control inputs, which are seamlessly integrated into the image generation pipeline. Experimental results show that StoryWeaver outperforms existing methods, particularly in maintaining consistency across characters.

The development of intelligent robots seeks to seamlessly integrate them into the human world, providing assistance and companionship in daily life and work, with the ultimate goal of achieving human-robot symbiosis. This requires robots with intelligent interaction abilities to work naturally and effectively with humans. However, current robotic simulators fail to support real human participation, limiting their ability to provide authentic interaction experiences and gather valuable human feedback essential for enhancing robotic capabilities. In this paper, we introduce SymBridge, the first human-in-the-loop cyber-physical interactive system designed to enable the safe and efficient development, evaluation, and optimization of human-robot interaction methods. Specifically, we employ augmented reality technology to enable real humans to interact with virtual robots in physical environments, creating an authentic interactive experience. Building on this, we propose a novel robotic interaction model that generates responsive, precise robot actions in real time through continuous human behavior observation. The model incorporates multi-resolution human motion features and environmental affordances, ensuring contextually adaptive robotic responses. Additionally, SymBridge enables continuous robot learning by collecting human feedback and dynamically adapting the robotic interaction model. By leveraging a carefully designed system architecture and modules, SymBridge builds a bridge between humans and robots, as well as between cyber and physical spaces, providing a natural and realistic online interaction experience while facilitating the continuous evolution of robotic intelligence. Extensive experiments, user studies, and real robot testing demonstrate the promising performance of the system and highlight its potential to significantly advance research on human-robot symbiosis.

3D Gaussian Splatting (3DGS) has witnessed exponential adoption across diverse applications, driving a critical need for semantic-aware 3D Gaussian representations to enable scene understanding and editing tasks. Existing approaches typically attach semantic features to a collection of free Gaussians and distill the features via differentiable rendering, leading to noisy segmentation and a messy selection of Gaussians. In this paper, we introduce AG^2aussian, a novel framework that leverages an anchor-graph structure to organize semantic features and regulate Gaussian primitives. Our anchor-graph structure not only promotes compact and instance-aware Gaussian distributions, but also facilitates graph-based propagation, achieving a clean and accurate instance-level Gaussian selection. Extensive validation across four applications, i.e. interactive click-based query, open-vocabulary text-driven query, object removal editing, and physics simulation, demonstrates the advantages of our approach and its benefits to various applications. The experiments and ablation studies further evaluate the effectiveness of the key designs of our approach.

Point cloud denoising task aims to recover the clean point cloud from the scanned data coupled with different levels or patterns of noise. The recent state-of-the-art methods often train deep neural networks to update the point locations towards the clean point cloud, and empirically repeat the denoising process several times in order to obtain the denoised results. It is not clear how to efficiently arrange the iterative denoising processes to deal with different levels or patterns of noise. In this paper, we propose an adaptive and iterative point cloud denoising method based on the score-based diffusion model. For a given noisy point cloud, we first estimate the noise variation and determine an adaptive denoising schedule with appropriate step sizes, then invoke the trained network iteratively to update point clouds following the adaptive schedule. To facilitate this adaptive and iterative denoising process, we design the network architecture and a two-stage sampling strategy for the network training to enable feature fusion and gradient fusion for iterative denoising. Compared to the state-of-the-art point cloud denoising methods, our approach obtains clean and smooth denoised point clouds, while preserving the shape boundary and details better. Our results not only outperform the other methods both qualitatively and quantitatively, but also are preferable on the synthetic dataset with different patterns of noises, as well as the real-scanned dataset.

Indoor scene synthesis aims to automatically produce plausible, realistic and diverse 3D indoor scenes, especially given arbitrary user requirements. Recently, the promising generalization ability of pre-trained large language models (LLM) assist in open-vocabulary indoor scene synthesis. However, the challenge lies in converting the LLM-generated outputs into reasonable and physically feasible scene layouts. In this paper, we propose to generate hierarchically structured scene descriptions with LLM and then compute the scene layouts. Specifically, we train a hierarchy-aware network to infer the fine-grained relative positions between objects and design a divide-and-conquer optimization to solve for scene layouts. The advantages of using hierarchically structured scene representation are two-fold. First, the hierarchical structure provides a rough grounding for object arrangement, which alleviates contradictory placements with dense relations and enhances the generalization ability of the network to infer fine-grained placements. Second, it naturally supports the divide-and-conquer optimization, by first arranging the sub-scenes and then the entire scene, to more effectively solve for a feasible layout. We conduct extensive comparison experiments and ablation studies with both qualitative and quantitative evaluations to validate the effectiveness of our key designs with the hierarchically structured scene representation. Our approach can generate more reasonable scene layouts while better aligned with the user requirements and LLM descriptions. We also present open-vocabulary scene synthesis and interactive scene design results to show the strength of our approach in the applications.

Recent advances in dexterous grasping synthesis have demonstrated significant progress in producing reasonable and plausible grasps for many task purposes. But it remains challenging to generalize to unseen object categories and diverse task instructions. In this paper, we propose G-DexGrasp, a retrieval-augmented generation approach that can produce high-quality dexterous hand configurations for unseen object categories and language-based task instructions. The key is to retrieve generalizable grasping priors, including the fine-grained contact part and the affordance-related distribution of relevant grasping instances, for the following synthesis pipeline. Specifically, the fine-grained contact part and affordance act as generalizable guidance to infer reasonable grasping configurations for unseen objects with a generative model, while the relevant grasping distribution plays as regularization to guarantee the plausibility of synthesized grasps during the subsequent refinement optimization. Our comparison experiments validate the effectiveness of our key designs for generalization and demonstrate the remarkable performance against the existing approaches. Project page: https://g-dexgrasp.github.io/

This report surveys advances in deep learning-based modeling techniques that address four different 3D indoor scene analysis tasks, as well as synthesis of 3D indoor scenes. We describe different kinds of representations for indoor scenes, various indoor scene datasets available for research in the aforementioned areas, and discuss notable works employing machine learning models for such scene modeling tasks based on these representations. Specifically, we focus on the analysis and synthesis of 3D indoor scenes. With respect to analysis, we focus on four basic scene understanding tasks -- 3D object detection, 3D scene segmentation, 3D scene reconstruction and 3D scene similarity. And for synthesis, we mainly discuss neural scene synthesis works, though also highlighting model-driven methods that allow for human-centric, progressive scene synthesis. We identify the challenges involved in modeling scenes for these tasks and the kind of machinery that needs to be developed to adapt to the data representation, and the task setting in general. For each of these tasks, we provide a comprehensive summary of the state-of-the-art works across different axes such as the choice of data representation, backbone, evaluation metric, input, output, etc., providing an organized review of the literature. Towards the end, we discuss some interesting research directions that have the potential to make a direct impact on the way users interact and engage with these virtual scene models, making them an integral part of the metaverse.

Geometric deep learning has sparked a rising interest in computer graphics to perform shape understanding tasks, such as shape classification and semantic segmentation. When the input is a polygonal surface, one has to suffer from the irregular mesh structure. Motivated by the geometric spectral theory, we introduce Laplacian2Mesh, a novel and flexible convolutional neural network (CNN) framework for coping with irregular triangle meshes (vertices may have any valence). By mapping the input mesh surface to the multi-dimensional Laplacian-Beltrami space, Laplacian2Mesh enables one to perform shape analysis tasks directly using the mature CNNs, without the need to deal with the irregular connectivity of the mesh structure. We further define a mesh pooling operation such that the receptive field of the network can be expanded while retaining the original vertex set as well as the connections between them. Besides, we introduce a channel-wise self-attention block to learn the individual importance of feature ingredients. Laplacian2Mesh not only decouples the geometry from the irregular connectivity of the mesh structure but also better captures the global features that are central to shape classification and segmentation. Extensive tests on various datasets demonstrate the effectiveness and efficiency of Laplacian2Mesh, particularly in terms of the capability of being vulnerable to noise to fulfill various learning tasks.

3D scene understanding and reconstruction aims to obtain a concise scene representation from images and reconstruct the complete scene, including the scene layout, objects bounding boxes and shapes. Existing holistic scene understanding methods primarily recover scenes from single images, with a focus on indoor scenes. Due to the complexity of real‐world, the information provided by a single image is limited, resulting in issues such as object occlusion and omission. Furthermore, captured data from outdoor scenes exhibits characteristics of sparsity, strong temporal dependencies and a lack of annotations. Consequently, the task of understanding and reconstructing outdoor scenes is highly challenging. The authors propose a sparse multi‐view images‐based 3D scene reconstruction framework (SMSR). It divides the scene reconstruction task into three stages: initial prediction, refinement, and fusion stage. The first two stages extract 3D scene representations from each viewpoint, while the final stage involves selection, calibration and fusion of object positions and orientations across different viewpoints. SMSR effectively address the issue of object omission by utilizing small‐scale sequential scene information. Experimental results on the general outdoor scene dataset UrbanScene3D‐Art Sci and our proprietary dataset Software College Aerial Time‐series Images, demonstrate that SMSR achieves superior performance in the scene understanding and reconstruction.

Deep generative models learn the data distribution, which is concentrated on a low-dimensional manifold. The geometric analysis of distribution transformation provides a better understanding of data structure and enables a variety of applications. In this paper, we study the geometric properties of the diffusion model, whose forward diffusion process and reverse generation process construct a series of distributions on manifolds which vary over time. Our key contribution is the introduction of generation rate, which corresponds to the local deformation of manifold over time around an image component. We show that the generation rate is highly correlated with intuitive visual properties, such as visual saliency, of the image component. Further, we propose an efficient and differentiable scheme to estimate the generation rate for a given image component over time, giving rise to a generation curve. The differentiable nature of our scheme allows us to control the shape of the generation curve via optimization. Using different loss functions, our generation curve matching algorithm provides a unified framework for a range of image manipulation tasks, including semantic transfer, object removal, saliency manipulation, image blending, etc. We conduct comprehensive analytical evaluations to support our findings and evaluate our framework on various manipulation tasks. The results show that our method consistently leads to better manipulation results, compared to recent baselines.

Point cloud understanding is an inherently challenging problem because of the sparse and unordered structure of the point cloud in the 3D space. Recently, Contrastive Vision-Language Pre-training (CLIP) based point cloud classification model i.e. PointCLIP has added a new direction in the point cloud classification research domain. In this method, at first multi-view depth maps are extracted from the point cloud and passed through the CLIP visual encoder. To transfer the 3D knowledge to the network, a small network called an adapter is fine-tuned on top of the CLIP visual encoder. PointCLIP has two limitations. Firstly, the point cloud depth maps lack image information which is essential for tasks like classification and recognition. Secondly, the adapter only relies on the global representation of the multi-view features. Motivated by this observation, we propose a Pretrained Point Cloud to Image Translation Network (PPCITNet) that produces generalized colored images along with additional salient visual cues to the point cloud depth maps so that it can achieve promising performance on point cloud classification and understanding. In addition, we propose a novel viewpoint adapter that combines the view feature processed by each viewpoint as well as the global intertwined knowledge that exists across the multi-view features. The experimental results demonstrate the superior performance of the proposed model over existing state-of-the-art CLIP-based models on ModelNet10, ModelNet40, and ScanobjectNN datasets.