Controllable Complex Human Motion Video Generation via Text-to-Skeleton Cascades
Department of Computer Science and Software Engineering, The University of Western Australia（计算机科学与软件工程系，西澳大学）；Munich Center for Machine Learning (MCML) and Technical University of Munich (TUM)（慕尼黑机器学习中心（MCML）和技术大学慕尼黑（TUM））；School of Information Technology, Murdoch University（信息科技学院，墨尔本大学）；Department of Electrical, Electronics and Computer Engineering, The University of Western Australia（电子、电子与计算机工程系，西澳大学）
Generating videos of complex human motions such as flips, cartwheels, and martial arts remains challenging for current video diffusion models. Text-only conditioning is temporally ambiguous for fine-grained motion control, while explicit pose-based controls, though effective, require users to provide complete skeleton sequences that are costly to produce for long and dynamic actions.
We propose a two-stage cascaded framework that addresses both limitations. First, an autoregressive text-to-skeleton model generates 2D pose sequences from natural language descriptions by predicting each joint conditioned on previously generated poses. This design captures long-range temporal dependencies and inter-joint coordination required for complex motions. Second, a pose-conditioned video diffusion model synthesizes videos from a reference image and the generated skeleton sequence. It employs DINO-ALF (Adaptive Layer Fusion), a multi-level reference encoder that preserves appearance and clothing details under large pose changes and self-occlusions.
To address the lack of publicly available datasets for complex human motion video generation, we introduce a Blender-based synthetic dataset containing 2,000 videos with diverse characters performing acrobatic and stunt-like motions. The dataset provides full control over appearance, motion, and environment. It fills an important gap because existing benchmarks significantly under-represent acrobatic motions while web-collected datasets raise copyright and privacy concerns.
Experiments on our synthetic dataset and the Motion-X Fitness benchmark show that our text-to-skeleton model outperforms prior methods on FID, R-precision, and motion diversity. Our pose-to-video model also achieves the best results among all compared methods on VBench metrics for temporal consistency, motion smoothness, and subject preservation.
University of Trento（特伦托大学）；Shenzhen Graduate School, Peking University（北京大学深圳研究生院）
We propose a unified Generative Adversarial Network (GAN) for controllable image-to-image translation, i.e., transferring an image from a source to a target domain guided by controllable structures. In addition to conditioning on a reference image, we show how the model can generate images conditioned on controllable structures, e.g., class labels, object keypoints, human skeletons, and scene semantic maps. The proposed model consists of a single generator and a discriminator taking a conditional image and the target controllable structure as input. In this way, the conditional image can provi…
Japan Advanced Institute of Science and Technology（日本先进科学技术学院）；The Chinese University of Hong Kong（香港中文大学）；Cornell University（康奈尔大学）；Shanghai Jiao Tong University（上海交通大学）
3D Scene-Adaptive Trajectory-Controllable Human Image Animation with Camera Movement
Engineering Research Center of Autonomous Unmanned System Technology（自主无人系统工程研究中心）；Ministry of Education（教育部）；Anhui Provincial Key Laboratory of Security Artificial Intelligence（安徽省安全人工智能重点实验室）；School of Artificial Intelligence, Anhui University（安徽大学人工智能学院）；University of Warwick（沃林格大学）；Zhejiang Yuexiu University（浙江越秀大学）；University of Surrey（萨里大学）
CCLAP: Controllable Chinese Landscape Painting Generation via Latent Diffusion Model
Beijing Institute of Technology（北京理工大学）；Institute of Computing Technology, Chinese Academy of Sciences（中国科学院计算技术研究所）；Institute of Intelligent Computing Technology, Chinese Academy of Sciences（中国科学院智能计算技术研究所）；Tomorrow Advancing Life（好未来）
Anatomy-Guided Residual Motion Diffusion for Controllable 4D Cardiac MRI Synthesis
Suzhou Institute of Biomedical Engineering and Technology, Chinese Academy of Science（中国科学院苏州生物医学工程技术研究所）；Systemes Complexes et Intelligence Artificielle, IMT Mines Ales（复杂系统与人工智能实验室，IMT 阿莱斯矿业学院）；School of Artificial Intelligence and Advanced Computing, Xi’an Jiaotong-Liverpool University（西交利物浦大学人工智能与先进计算学院）
Improving Text-guided Object Inpainting with Semantic Pre-inpainting
School of Computer Science, Fudan University（复旦大学计算机科学学院）；HiDream.ai Inc.（HiDream.ai公司）；Shanghai Collaborative Innovation Center of Intelligent Visual Computing（上海智能视觉计算协同创新中心）
Cross-Block Fine-Grained Semantic Cascade for Skeleton-Based Sports Action Recognition
School of Automation, Southeast University（东南大学自动化学院）；School of Instrument Science and Engineering, Southeast University（东南大学仪器科学与工程学院）；Department of Computer and Information Science, University of Massachusetts Dartmouth（马萨诸塞大学达特茅斯分校计算机与信息科学系）
UniMC: Taming Diffusion Transformer for Unified Keypoint-Guided Multi-Class Image Generation
The Hong Kong University of Science and Technology（香港科学与技术大学）；The University of Hong Kong（香港大学）；The Chinese University of Hong Kong（香港中文大学）；Peking University（北京大学）；Tencent（腾讯）；National University of Singapore（新加坡国立大学）
University of Hong Kong（香港大学）；Max Planck Institute for Informatics（马克斯·普朗克信息学研究所）；Stanford University（斯坦福大学）
We propose a method for generating video-realistic animations of real humans under user control. In contrast to conventional human character rendering, we do not require the availability of a production-quality photo-realistic 3D model of the human, but instead rely on a video sequence in conjunction with a (medium-quality) controllable 3D template model of the person. With that, our approach significantly reduces production cost compared to conventional rendering approaches based on production-quality 3D models, and can also be used to realistically edit existing videos. Technically, this is …
DisPose: Disentangling Pose Guidance for Controllable Human Image Animation
Peking University（北京大学）；University of Science and Technology of China（中国科学技术大学）；Tsinghua University（清华大学）；Hong Kong University of Science and Technology（香港科技大学）
To be truly understandable and accepted by Deaf communities, an automatic Sign Language Production (SLP) system must generate a photo-realistic signer. Prior approaches based on graphical avatars have proven unpopular, whereas recent neural SLP works that produce skeleton pose sequences have been shown to be not understandable to Deaf viewers. In this paper, we propose SignGAN, the first SLP model to produce photo-realistic continuous sign language videos directly from spoken language. We employ a transformer architecture with a Mixture Density Network (MDN) formulation to handle the translati…
Shanghai Jiao Tong University（上海交通大学）；Shanghai AI Laboratory（上海人工智能实验室）；Zhejiang University（浙江大学）；Huawei Cloud & AI（华为云与人工智能）
Graph convolutional network based methods that model the body-joints' relations, have recently shown great promise in 3D skeleton-based human motion prediction. However, these methods have two critical issues: first, deep graph convolutions filter features within only limited graph spectrums, losing sufficient information in the full band; second, using a single graph to model the whole body underestimates the diverse patterns on various body-parts. To address the first issue, we propose adaptive graph scattering, which leverages multiple trainable band-pass graph filters to decompose pose fea…
Training large-scale image captioning (IC) models demands access to a rich and diverse set of training examples, gathered from the wild, often from noisy alt-text data. However, recent modeling approaches to IC often fall short in terms of performance in this case, because they assume a clean annotated dataset (as opposed to the noisier alt-text--based annotations), and employ an end-to-end generation approach, which often lacks both controllability and interpretability. We address these problems by breaking down the task into two simpler, more controllable tasks -- skeleton prediction and ske…
TriHuman : A Real-time and Controllable Tri-plane Representation for Detailed Human Geometry and Appearance Synthesis
Max Planck Institute for Informatics（马克斯·普朗克信息学研究所）；Saarland Informatics Campus（萨尔兰信息学园区）；Saarbrücken Research Center for Visual Computing, Interaction and AI（萨尔布吕肯视觉计算、交互与人工智能研究中心）
The Hong Kong University of Science and Technology（香港科技大学）；Tencent（腾讯）
End-to-end deep representation learning has achieved remarkable accuracy for monocular 3D human pose estimation, yet these models may fail for unseen poses with limited and fixed training data. This paper proposes a novel data augmentation method that: (1) is scalable for synthesizing massive amount of training data (over 8 million valid 3D human poses with corresponding 2D projections) for training 2D-to-3D networks, (2) can effectively reduce dataset bias. Our method evolves a limited dataset to synthesize unseen 3D human skeletons based on a hierarchical human representation and heuristics …
DAMO Academy, Alibaba Group（阿里巴巴集团达摩院）；Nanyang Technological University（南洋理工大学）；Beijing University of Posts and Telecommunications（北京邮电大学）
The 3D pose estimation from a single image is a challenging problem due to depth ambiguity. One type of the previous methods lifts 2D joints, obtained by resorting to external 2D pose detectors, to the 3D space. However, this type of approaches discards the contextual information of images which are strong cues for 3D pose estimation. Meanwhile, some other methods predict the joints directly from monocular images but adopt a 2.5D output representation $P^{2.5D} = (u,v,z^{r}) $ where both $u$ and $v$ are in the image space but $z^{r}$ in root-relative 3D space. Thus, the ground-truth informatio…
The University of Sydney（悉尼大学）；Shanghai AI Laboratory（上海人工智能实验室）；Netease Fuxi AI Lab（网易伏羲人工智能实验室）
Synthesizing controllable motion for a character using deep learning has been a promising approach due to its potential to learn a compact model without laborious feature engineering. To produce dynamic motion from weak control signals such as desired paths, existing methods often require auxiliary information such as phases for alleviating motion ambiguity, which limits their generalisation capability. As past poses often contain useful auxiliary hints, in this paper, we propose a task-agnostic deep learning method, namely Multi-scale Control Signal-aware Transformer (MCS-T), with an attentio…
Body reshaping is an important procedure in portrait photo retouching. Due to the complicated structure and multifarious appearance of human bodies, existing methods either fall back on the 3D domain via body morphable model or resort to keypoint-based image deformation, leading to inefficiency and unsatisfied visual quality. In this paper, we address these limitations by formulating an end-to-end flow generation architecture under the guidance of body structural priors, including skeletons and Part Affinity Fields, and achieve unprecedentedly controllable performance under arbitrary poses and…
Shandong University（山东大学）；University of Central Florida（中佛罗里达大学）；Amazon Prime Video（亚马逊Prime Video）；Peking University（北京大学）
Recently, transformer-based methods have gained significant success in sequential 2D-to-3D lifting human pose estimation. As a pioneering work, PoseFormer captures spatial relations of human joints in each video frame and human dynamics across frames with cascaded transformer layers and has achieved impressive performance. However, in real scenarios, the performance of PoseFormer and its follow-ups is limited by two factors: (a) The length of the input joint sequence; (b) The quality of 2D joint detection. Existing methods typically apply self-attention to all frames of the input sequence, cau…
