Lingting Zhu

Lingting Zhu, Xian Liu, Xuanyu Liu et al.

Animating virtual avatars to make co-speech gestures facilitates various applications in human-machine interaction. The existing methods mainly rely on generative adversarial networks (GANs), which typically suffer from notorious mode collapse and unstable training, thus making it difficult to learn accurate audio-gesture joint distributions. In this work, we propose a novel diffusion-based framework, named Diffusion Co-Speech Gesture (DiffGesture), to effectively capture the cross-modal audio-to-gesture associations and preserve temporal coherence for high-fidelity audio-driven co-speech gesture generation. Specifically, we first establish the diffusion-conditional generation process on clips of skeleton sequences and audio to enable the whole framework. Then, a novel Diffusion Audio-Gesture Transformer is devised to better attend to the information from multiple modalities and model the long-term temporal dependency. Moreover, to eliminate temporal inconsistency, we propose an effective Diffusion Gesture Stabilizer with an annealed noise sampling strategy. Benefiting from the architectural advantages of diffusion models, we further incorporate implicit classifier-free guidance to trade off between diversity and gesture quality. Extensive experiments demonstrate that DiffGesture achieves state-of-theart performance, which renders coherent gestures with better mode coverage and stronger audio correlations. Code is available at https://github.com/Advocate99/DiffGesture.

Zhenchao Jin, Xiaowei Hu, Lingting Zhu et al.

Co-occurrent visual patterns suggest that pixel relation modeling facilitates dense prediction tasks, which inspires the development of numerous context modeling paradigms, \emph{e.g.}, multi-scale-driven and similarity-driven context schemes. Despite the impressive results, these existing paradigms often suffer from inadequate or ineffective contextual information aggregation due to reliance on large amounts of predetermined priors. To alleviate the issues, we propose a novel \textbf{I}ntervention-\textbf{D}riven \textbf{R}elation \textbf{Net}work (\textbf{IDRNet}), which leverages a deletion diagnostics procedure to guide the modeling of contextual relations among different pixels. Specifically, we first group pixel-level representations into semantic-level representations with the guidance of pseudo labels and further improve the distinguishability of the grouped representations with a feature enhancement module. Next, a deletion diagnostics procedure is conducted to model relations of these semantic-level representations via perceiving the network outputs and the extracted relations are utilized to guide the semantic-level representations to interact with each other. Finally, the interacted representations are utilized to augment original pixel-level representations for final predictions. Extensive experiments are conducted to validate the effectiveness of IDRNet quantitatively and qualitatively. Notably, our intervention-driven context scheme brings consistent performance improvements to state-of-the-art segmentation frameworks and achieves competitive results on popular benchmark datasets, including ADE20K, COCO-Stuff, PASCAL-Context, LIP, and Cityscapes. Code is available at \url{https://github.com/SegmentationBLWX/sssegmentation}.

Lingting Zhu, Zeyue Xue, Zhenchao Jin et al.

Cross-modality medical image synthesis is a critical topic and has the potential to facilitate numerous applications in the medical imaging field. Despite recent successes in deep-learning-based generative models, most current medical image synthesis methods rely on generative adversarial networks and suffer from notorious mode collapse and unstable training. Moreover, the 2D backbone-driven approaches would easily result in volumetric inconsistency, while 3D backbones are challenging and impractical due to the tremendous memory cost and training difficulty. In this paper, we introduce a new paradigm for volumetric medical data synthesis by leveraging 2D backbones and present a diffusion-based framework, Make-A-Volume, for cross-modality 3D medical image synthesis. To learn the cross-modality slice-wise mapping, we employ a latent diffusion model and learn a low-dimensional latent space, resulting in high computational efficiency. To enable the 3D image synthesis and mitigate volumetric inconsistency, we further insert a series of volumetric layers in the 2D slice-mapping model and fine-tune them with paired 3D data. This paradigm extends the 2D image diffusion model to a volumetric version with a slightly increasing number of parameters and computation, offering a principled solution for generic cross-modality 3D medical image synthesis. We showcase the effectiveness of our Make-A-Volume framework on an in-house SWI-MRA brain MRI dataset and a public T1-T2 brain MRI dataset. Experimental results demonstrate that our framework achieves superior synthesis results with volumetric consistency.

Ning Lu, Baijiong Lin, Shengcai Liu et al.

Reinforcement learning (RL) improves large language model (LLM) agents by teaching them which actions lead to high rewards, but provides little supervision on what those actions do to the environment. World modeling (WM) can fill this gap, yet existing approaches often require separate simulators, extra training stages, or additional inference-time computation. We observe that on-policy RL rollouts already contain the needed signal: each transition pairs an action with its resulting next observation. Based on this observation, we propose PaW, a Policy and World modeling co-training framework that adds auxiliary WM supervision to the same policy during RL, without changing the inference paradigm. To make auxiliary WM supervision informative and stable, PaW introduces three components: action-entropy-based WM data selection, noise-tolerant WM loss, and reward-adaptive loss balancing. Experiments on three agentic task benchmarks show consistent improvements over strong RL baselines across models and RL algorithms. These results suggest that standard RL rollouts are a practical source of WM supervision for language-agent training.

Weijia Feng, Lingting Zhu, Lequan Yu

The Segment Anything Model (SAM) has demonstrated remarkable capabilities of scaled-up segmentation models, enabling zero-shot generalization across a variety of domains. By leveraging large-scale foundational models as pre-trained models, it is a natural progression to fine-tune SAM for specific domains to further enhance performances. However, the adoption of foundational models in the medical domain presents a challenge due to the difficulty and expense of labeling sufficient data for adaptation within hospital systems. In this paper, we introduce an efficient and practical approach for fine-tuning SAM using a limited number of exemplars, making it suitable for such scenarios. Our approach combines two established techniques from the literature: an exemplar-guided synthesis module and the widely recognized Low-Rank Adaptation (LoRA) fine-tuning strategy, serving as data-level and model-level attempts respectively. Interestingly, our empirical findings suggest that SAM can be effectively aligned within the medical domain even with few labeled data. We validate our approach through experiments on brain tumor segmentation (BraTS) and multi-organ CT segmentation (Synapse). The comprehensive results underscore the feasibility and effectiveness of such an approach, paving the way for the practical application of SAM in the medical domain.

Lingting Zhu, Shengju Qian, Haidi Fan et al.

The digital industry demands high-quality, diverse modular 3D assets, especially for user-generated content~(UGC). In this work, we introduce AssetFormer, an autoregressive Transformer-based model designed to generate modular 3D assets from textual descriptions. Our pilot study leverages real-world modular assets collected from online platforms. AssetFormer tackles the challenge of creating assets composed of primitives that adhere to constrained design parameters for various applications. By innovatively adapting module sequencing and decoding techniques inspired by language models, our approach enhances asset generation quality through autoregressive modeling. Initial results indicate the effectiveness of AssetFormer in streamlining asset creation for professional development and UGC scenarios. This work presents a flexible framework extendable to various types of modular 3D assets, contributing to the broader field of 3D content generation. The code is available at https://github.com/Advocate99/AssetFormer.

Lingting Zhu, Guying Lin, Jinnan Chen et al.

While Implicit Neural Representations (INRs) have demonstrated significant success in image representation, they are often hindered by large training memory and slow decoding speed. Recently, Gaussian Splatting (GS) has emerged as a promising solution in 3D reconstruction due to its high-quality novel view synthesis and rapid rendering capabilities, positioning it as a valuable tool for a broad spectrum of applications. In particular, a GS-based representation, 2DGS, has shown potential for image fitting. In our work, we present \textbf{L}arge \textbf{I}mages are \textbf{G}aussians (\textbf{LIG}), which delves deeper into the application of 2DGS for image representations, addressing the challenge of fitting large images with 2DGS in the situation of numerous Gaussian points, through two distinct modifications: 1) we adopt a variant of representation and optimization strategy, facilitating the fitting of a large number of Gaussian points; 2) we propose a Level-of-Gaussian approach for reconstructing both coarse low-frequency initialization and fine high-frequency details. Consequently, we successfully represent large images as Gaussian points and achieve high-quality large image representation, demonstrating its efficacy across various types of large images. Code is available at {\href{https://github.com/HKU-MedAI/LIG}{https://github.com/HKU-MedAI/LIG}}.

Lingting Zhu, Yizheng Chen, Lianli Liu et al.

Multi-modality imaging is widely used in clinical practice and biomedical research to gain a comprehensive understanding of an imaging subject. Currently, multi-modality imaging is accomplished by post hoc fusion of independently reconstructed images under the guidance of mutual information or spatially registered hardware, which limits the accuracy and utility of multi-modality imaging. Here, we investigate a data-driven multi-modality imaging (DMI) strategy for synergetic imaging of CT and MRI. We reveal two distinct types of features in multi-modality imaging, namely intra- and inter-modality features, and present a multi-sensor learning (MSL) framework to utilize the crossover inter-modality features for augmented multi-modality imaging. The MSL imaging approach breaks down the boundaries of traditional imaging modalities and allows for optimal hybridization of CT and MRI, which maximizes the use of sensory data. We showcase the effectiveness of our DMI strategy through synergetic CT-MRI brain imaging. The principle of DMI is quite general and holds enormous potential for various DMI applications across disciplines.

Chenyu Liu, Hongze Chen, Jingzhi Bao et al.

Despite major advances brought by diffusion-based models, current 3D texture generation systems remain hindered by cross-view inconsistency -- textures that appear convincing from one viewpoint often fail to align across others. We find that this issue arises from attention ambiguity, where unstructured full attention is applied indiscriminately across tokens and modalities, causing geometric confusion and unstable appearance-structure coupling. To address this, we introduce CaliTex, a framework of geometry-calibrated attention that explicitly aligns attention with 3D structure. It introduces two modules: Part-Aligned Attention that enforces spatial alignment across semantically matched parts, and Condition-Routed Attention which routes appearance information through geometry-conditioned pathways to maintain spatial fidelity. Coupled with a two-stage diffusion transformer, CaliTex makes geometric coherence an inherent behavior of the network rather than a byproduct of optimization. Empirically, CaliTex produces seamless and view-consistent textures and outperforms both open-source and commercial baselines.

Jingzhi Bao, Hongze Chen, Lingting Zhu et al.

Physically-based rendering (PBR) provides a principled standard for realistic material-lighting interactions in computer graphics. Despite recent advances in generating PBR textures, existing methods fail to address two fundamental challenges: 1) materials decomposition from image prompts under limited illumination cues, and 2) seamless and view-consistent texture completion. To this end, we propose LumiTex, an end-to-end framework that comprises three key components: (1) a multi-branch generation scheme that disentangles albedo and metallic-roughness under shared illumination priors for robust material understanding, (2) a lighting-aware material attention mechanism that injects illumination context into the decoding process for physically grounded generation of albedo, metallic, and roughness maps, and (3) a geometry-guided inpainting module based on a large view synthesis model that enriches texture coverage and ensures seamless, view-consistent UV completion. Extensive experiments demonstrate that LumiTex achieves state-of-the-art performance in texture quality, surpassing both existing open-source and commercial methods.

Lingting Zhu, Noel Codella, Dongdong Chen et al.

The limited availability of 3D medical image datasets, due to privacy concerns and high collection or annotation costs, poses significant challenges in the field of medical imaging. While a promising alternative is the use of synthesized medical data, there are few solutions for realistic 3D medical image synthesis due to difficulties in backbone design and fewer 3D training samples compared to 2D counterparts. In this paper, we propose GEM-3D, a novel generative approach to the synthesis of 3D medical images and the enhancement of existing datasets using conditional diffusion models. Our method begins with a 2D slice, noted as the informed slice to serve the patient prior, and propagates the generation process using a 3D segmentation mask. By decomposing the 3D medical images into masks and patient prior information, GEM-3D offers a flexible yet effective solution for generating versatile 3D images from existing datasets. GEM-3D can enable dataset enhancement by combining informed slice selection and generation at random positions, along with editable mask volumes to introduce large variations in diffusion sampling. Moreover, as the informed slice contains patient-wise information, GEM-3D can also facilitate counterfactual image synthesis and dataset-level de-enhancement with desired control. Experiments on brain MRI and abdomen CT images demonstrate that GEM-3D is capable of synthesizing high-quality 3D medical images with volumetric consistency, offering a straightforward solution for dataset enhancement during inference. The code is available at https://github.com/HKU-MedAI/GEM-3D.

Lingting Zhu, Zhao Wang, Jiahao Cui et al.

Surgical 3D reconstruction is a critical area of research in robotic surgery, with recent works adopting variants of dynamic radiance fields to achieve success in 3D reconstruction of deformable tissues from single-viewpoint videos. However, these methods often suffer from time-consuming optimization or inferior quality, limiting their adoption in downstream tasks. Inspired by 3D Gaussian Splatting, a recent trending 3D representation, we present EndoGS, applying Gaussian Splatting for deformable endoscopic tissue reconstruction. Specifically, our approach incorporates deformation fields to handle dynamic scenes, depth-guided supervision with spatial-temporal weight masks to optimize 3D targets with tool occlusion from a single viewpoint, and surface-aligned regularization terms to capture the much better geometry. As a result, EndoGS reconstructs and renders high-quality deformable endoscopic tissues from a single-viewpoint video, estimated depth maps, and labeled tool masks. Experiments on DaVinci robotic surgery videos demonstrate that EndoGS achieves superior rendering quality. Code is available at https://github.com/HKU-MedAI/EndoGS.

Zeyue Xue, Jie Wu, Yu Gao et al.

Recent advances in generative AI have revolutionized visual content creation, yet aligning model outputs with human preferences remains a critical challenge. While Reinforcement Learning (RL) has emerged as a promising approach for fine-tuning generative models, existing methods like DDPO and DPOK face fundamental limitations - particularly their inability to maintain stable optimization when scaling to large and diverse prompt sets, severely restricting their practical utility. This paper presents DanceGRPO, a framework that addresses these limitations through an innovative adaptation of Group Relative Policy Optimization (GRPO) for visual generation tasks. Our key insight is that GRPO's inherent stability mechanisms uniquely position it to overcome the optimization challenges that plague prior RL-based approaches on visual generation. DanceGRPO establishes several significant advances: First, it demonstrates consistent and stable policy optimization across multiple modern generative paradigms, including both diffusion models and rectified flows. Second, it maintains robust performance when scaling to complex, real-world scenarios encompassing three key tasks and four foundation models. Third, it shows remarkable versatility in optimizing for diverse human preferences as captured by five distinct reward models assessing image/video aesthetics, text-image alignment, video motion quality, and binary feedback. Our comprehensive experiments reveal that DanceGRPO outperforms baseline methods by up to 181\% across multiple established benchmarks, including HPS-v2.1, CLIP Score, VideoAlign, and GenEval. Our results establish DanceGRPO as a robust and versatile solution for scaling Reinforcement Learning from Human Feedback (RLHF) tasks in visual generation, offering new insights into harmonizing reinforcement learning and visual synthesis.

Yifan Li, Yingda Yin, Lingting Zhu et al.

Reasoning-centric video object segmentation is an inherently complex task: the query often refers to dynamics, causality, and temporal interactions, rather than static appearances. Yet existing solutions generally collapse these factors into simplified reasoning with latent embeddings, rendering the reasoning chain opaque and essentially intractable. We therefore adopt an explicit decomposition perspective and introduce ReVSeg, which executes reasoning as sequential decisions in the native interface of pretrained vision language models (VLMs). Rather than folding all reasoning into a single-step prediction, ReVSeg executes three explicit operations -- semantics interpretation, temporal evidence selection, and spatial grounding -- aligning pretrained capabilities. We further employ reinforcement learning to optimize the multi-step reasoning chain, enabling the model to self-refine its decision quality from outcome-driven signals. Experimental results demonstrate that ReVSeg attains state-of-the-art performances on standard video object segmentation benchmarks and yields interpretable reasoning trajectories. Project page is available at https://clementine24.github.io/ReVSeg/ .

Yi Wu, Lingting Zhu, Lei Liu et al.

Multimodal autoregressive (AR) models, based on next-token prediction and transformer architecture, have demonstrated remarkable capabilities in various multimodal tasks including text-to-image (T2I) generation. Despite their strong performance in general T2I tasks, our research reveals that these models initially struggle with subject-driven image generation compared to dominant diffusion models. To address this limitation, we introduce Proxy-Tuning, leveraging diffusion models to enhance AR models' capabilities in subject-specific image generation. Our method reveals a striking weak-to-strong phenomenon: fine-tuned AR models consistently outperform their diffusion model supervisors in both subject fidelity and prompt adherence. We analyze this performance shift and identify scenarios where AR models excel, particularly in multi-subject compositions and contextual understanding. This work not only demonstrates impressive results in subject-driven AR image generation, but also unveils the potential of weak-to-strong generalization in the image generation domain, contributing to a deeper understanding of different architectures' strengths and limitations.

Jinnan Chen, Lingting Zhu, Zeyu Hu et al.

Recent advances in auto-regressive transformers have revolutionized generative modeling across different domains, from language processing to visual generation, demonstrating remarkable capabilities. However, applying these advances to 3D generation presents three key challenges: the unordered nature of 3D data conflicts with sequential next-token prediction paradigm, conventional vector quantization approaches incur substantial compression loss when applied to 3D meshes, and the lack of efficient scaling strategies for higher resolution latent prediction. To address these challenges, we introduce MAR-3D, which integrates a pyramid variational autoencoder with a cascaded masked auto-regressive transformer (Cascaded MAR) for progressive latent upscaling in the continuous space. Our architecture employs random masking during training and auto-regressive denoising in random order during inference, naturally accommodating the unordered property of 3D latent tokens. Additionally, we propose a cascaded training strategy with condition augmentation that enables efficiently up-scale the latent token resolution with fast convergence. Extensive experiments demonstrate that MAR-3D not only achieves superior performance and generalization capabilities compared to existing methods but also exhibits enhanced scaling capabilities compared to joint distribution modeling approaches (e.g., diffusion transformers).

Lingting Zhu, Jingrui Ye, Runze Zhang et al.

Current methods for 3D generation still fall short in physically based rendering (PBR) texturing, primarily due to limited data and challenges in modeling multi-channel materials. In this work, we propose MuMA, a method for 3D PBR texturing through Multi-channel Multi-view generation and Agentic post-processing. Our approach features two key innovations: 1) We opt to model shaded and albedo appearance channels, where the shaded channels enables the integration intrinsic decomposition modules for material properties. 2) Leveraging multimodal large language models, we emulate artists' techniques for material assessment and selection. Experiments demonstrate that MuMA achieves superior results in visual quality and material fidelity compared to existing methods.

Zhao Wang, Hao Wen, Lingting Zhu et al.

Character video generation is a significant real-world application focused on producing high-quality videos featuring specific characters. Recent advancements have introduced various control signals to animate static characters, successfully enhancing control over the generation process. However, these methods often lack flexibility, limiting their applicability and making it challenging for users to synthesize a source character into a desired target scene. To address this issue, we propose a novel framework, AnyCharV, that flexibly generates character videos using arbitrary source characters and target scenes, guided by pose information. Our approach involves a two-stage training process. In the first stage, we develop a base model capable of integrating the source character with the target scene using pose guidance. The second stage further bootstraps controllable generation through a self-boosting mechanism, where we use the generated video in the first stage and replace the fine mask with the coarse one, enabling training outcomes with better preservation of character details. Extensive experimental results demonstrate the superiority of our method compared with previous state-of-the-art methods.

Yang Luo, Xuanlei Zhao, Baijiong Lin et al.

Recent progress in generative video models, such as Veo-3, has shown surprising zero-shot reasoning abilities, creating a growing need for systematic and reliable evaluation. We introduce V-ReasonBench, a benchmark designed to assess video reasoning across four key dimensions: structured problem-solving, spatial cognition, pattern-based inference, and physical dynamics. The benchmark is built from both synthetic and real-world image sequences and provides a diverse set of answer-verifiable tasks that are reproducible, scalable, and unambiguous. Evaluations of six state-of-the-art video models reveal clear dimension-wise differences, with strong variation in structured, spatial, pattern-based, and physical reasoning. We further compare video models with strong image models, analyze common hallucination behaviors, and study how video duration affects Chain-of-Frames reasoning. Overall, V-ReasonBench offers a unified and reproducible framework for measuring video reasoning and aims to support the development of models with more reliable, human-aligned reasoning skills.

Jingrui Ye, Lingting Zhu, Runze Zhang et al.

The increasing demand for 3D assets across various industries necessitates efficient and automated methods for 3D content creation. Leveraging 3D Gaussian Splatting, recent large reconstruction models (LRMs) have demonstrated the ability to efficiently achieve high-quality 3D rendering by integrating multiview diffusion for generation and scalable transformers for reconstruction. However, existing models fail to produce the material properties of assets, which is crucial for realistic rendering in diverse lighting environments. In this paper, we introduce the Large Material Gaussian Model (MGM), a novel framework designed to generate high-quality 3D content with Physically Based Rendering (PBR) materials, ie, albedo, roughness, and metallic properties, rather than merely producing RGB textures with uncontrolled light baking. Specifically, we first fine-tune a new multiview material diffusion model conditioned on input depth and normal maps. Utilizing the generated multiview PBR images, we explore a Gaussian material representation that not only aligns with 2D Gaussian Splatting but also models each channel of the PBR materials. The reconstructed point clouds can then be rendered to acquire PBR attributes, enabling dynamic relighting by applying various ambient light maps. Extensive experiments demonstrate that the materials produced by our method not only exhibit greater visual appeal compared to baseline methods but also enhance material modeling, thereby enabling practical downstream rendering applications.

Jingfeng Guo, Jinnan Chen, Weikai Chen et al.

This work presents GarmentX, a novel framework for generating diverse, high-fidelity, and wearable 3D garments from a single input image. Traditional garment reconstruction methods directly predict 2D pattern edges and their connectivity, an overly unconstrained approach that often leads to severe self-intersections and physically implausible garment structures. In contrast, GarmentX introduces a structured and editable parametric representation compatible with GarmentCode, ensuring that the decoded sewing patterns always form valid, simulation-ready 3D garments while allowing for intuitive modifications of garment shape and style. To achieve this, we employ a masked autoregressive model that sequentially predicts garment parameters, leveraging autoregressive modeling for structured generation while mitigating inconsistencies in direct pattern prediction. Additionally, we introduce GarmentX dataset, a large-scale dataset of 378,682 garment parameter-image pairs, constructed through an automatic data generation pipeline that synthesizes diverse and high-quality garment images conditioned on parametric garment representations. Through integrating our method with GarmentX dataset, we achieve state-of-the-art performance in geometric fidelity and input image alignment, significantly outperforming prior approaches. We will release GarmentX dataset upon publication.

Jinnan Chen, Chen Li, Jianfeng Zhang et al.

In this work, we tackle the task of learning 3D human Gaussians from a single image, focusing on recovering detailed appearance and geometry including unobserved regions. We introduce a single-view generalizable Human Gaussian Model (HGM), which employs a novel generate-then-refine pipeline with the guidance from human body prior and diffusion prior. Our approach uses a ControlNet to refine rendered back-view images from coarse predicted human Gaussians, then uses the refined image along with the input image to reconstruct refined human Gaussians. To mitigate the potential generation of unrealistic human poses and shapes, we incorporate human priors from the SMPL-X model as a dual branch, propagating image features from the SMPL-X volume to the image Gaussians using sparse convolution and attention mechanisms. Given that the initial SMPL-X estimation might be inaccurate, we gradually refine it with our HGM model. We validate our approach on several publicly available datasets. Our method surpasses previous methods in both novel view synthesis and surface reconstruction. Our approach also exhibits strong generalization for cross-dataset evaluation and in-the-wild images.

Zhao Wang, Aoxue Li, Lingting Zhu et al.

Customized text-to-video generation aims to generate high-quality videos guided by text prompts and subject references. Current approaches for personalizing text-to-video generation suffer from tackling multiple subjects, which is a more challenging and practical scenario. In this work, our aim is to promote multi-subject guided text-to-video customization. We propose CustomVideo, a novel framework that can generate identity-preserving videos with the guidance of multiple subjects. To be specific, firstly, we encourage the co-occurrence of multiple subjects via composing them in a single image. Further, upon a basic text-to-video diffusion model, we design a simple yet effective attention control strategy to disentangle different subjects in the latent space of diffusion model. Moreover, to help the model focus on the specific area of the object, we segment the object from given reference images and provide a corresponding object mask for attention learning. Also, we collect a multi-subject text-to-video generation dataset as a comprehensive benchmark. Extensive qualitative, quantitative, and user study results demonstrate the superiority of our method compared to previous state-of-the-art approaches. The project page is https://kyfafyd.wang/projects/customvideo.