Generating stable and controllable character motion in real-time is a key challenge in computer animation. Existing methods often fail to provide fine-grained control or suffer from motion degradation over long sequences, limiting their use in interactive applications. We propose COMET, an autoregressive framework that runs in real time, enabling versatile character control and robust long-horizon synthesis. Our efficient Transformer-based conditional VAE allows for precise, interactive control over arbitrary user-specified joints for tasks like goal-reaching and in-betweening from a single model. To ensure long-term temporal stability, we introduce a novel reference-guided feedback mechanism that prevents error accumulation. This mechanism also serves as a plug-and-play stylization module, enabling real-time style transfer. Extensive evaluations demonstrate that COMET robustly generates high-quality motion at real-time speeds, significantly outperforming state-of-the-art approaches in complex motion control tasks and confirming its readiness for demanding interactive applications.
UniGP: Taming Diffusion Transformer for Prior-Preserved Unified Generation and Perception
The Hong Kong University of Science and Technology（香港科学与技术大学）；DAMO Academy, Alibaba Group（阿里云达摩院）；Hupan Lab（虎扑实验室）；Zhejiang University（浙江大学）；Tsinghua University（清华大学）；The Chinese University of Hong Kong（香港中文大学）；Zeekr Automobile R&D Co., Ltd.（小鹏汽车研发有限公司）
Recent studies have shown that StyleGANs provide promising prior models for downstream tasks on image synthesis and editing. However, since the latent codes of StyleGANs are designed to control global styles, it is hard to achieve a fine-grained control over synthesized images. We present SemanticStyleGAN, where a generator is trained to model local semantic parts separately and synthesizes images in a compositional way. The structure and texture of different local parts are controlled by corresponding latent codes. Experimental results demonstrate that our model provides a strong disentanglem…
ReImagine: Rethinking Controllable High-Quality Human Video Generation via Image-First Synthesis
School of Science and Engineering, The Chinese University of Hong Kong, Shenzhen（香港中文大学（深圳）科学与工程学院）；Future Network of Intelligence Institute, CUHK-Shenzhen, China（CUHK-深圳智能网络研究院）
Universidade Federal de Minas Gerais（米纳斯吉拉斯联邦大学）；Université Bourgogne Franche-Comté（勃艮第-弗朗什-孔泰大学）
This paper proposes a new end-to-end neural rendering architecture to transfer appearance and reenact human actors. Our method leverages a carefully designed graph convolutional network (GCN) to model the human body manifold structure, jointly with differentiable rendering, to synthesize new videos of people in different contexts from where they were initially recorded. Unlike recent appearance transferring methods, our approach can reconstruct a fully controllable 3D texture-mapped model of a person, while taking into account the manifold structure from body shape and texture appearance in th…
Chinese University of Hong Kong（香港中文大学）；Texas A&M University（得克萨斯农工大学）
Flow-based generative models show great potential in image synthesis due to its reversible pipeline and exact log-likelihood target, yet it suffers from weak ability for conditional image synthesis, especially for multi-label or unaware conditions. This is because the potential distribution of image conditions is hard to measure precisely from its latent variable $z$. In this paper, based on modeling a joint probabilistic density of an image and its conditions, we propose a novel flow-based generative model named conditional adversarial generative flow (CAGlow). Instead of disentangling attrib…
In the present study, we propose to implement a new framework for estimating generative models via an adversarial process to extend an existing GAN framework and develop a white-box controllable image cartoonization, which can generate high-quality cartooned images/videos from real-world photos and videos. The learning purposes of our system are based on three distinct representations: surface representation, structure representation, and texture representation. The surface representation refers to the smooth surface of the images. The structure representation relates to the sparse colour bloc…
Warsaw University of Technology（华沙理工大学）；Microsoft（微软）；Tooploox；Jagiellonian University（雅盖隆大学）
The creation of plausible and controllable 3D human motion animations is a long-standing problem that requires a manual intervention of skilled artists. Current machine learning approaches can semi-automate the process, however, they are limited in a significant way: they can handle only a single trajectory of the expected motion that precludes fine-grained control over the output. To mitigate that issue, we reformulate the problem of future pose prediction into pose completion in space and time where multiple trajectories are represented as poses with missing joints. We show that such a frame…
Controllable generation is one of the key requirements for successful adoption of deep generative models in real-world applications, but it still remains as a great challenge. In particular, the compositional ability to generate novel concept combinations is out of reach for most current models. In this work, we use energy-based models (EBMs) to handle compositional generation over a set of attributes. To make them scalable to high-resolution image generation, we introduce an EBM in the latent space of a pre-trained generative model such as StyleGAN. We propose a novel EBM formulation represen…
Due to the cost or interference of measurement, we need to control measurement system. Assuming that each variable can be measured sequentially, there exists optimal policy choosing next measurement for the former observations. Though optimal measurement policy is actually dependent on the goal of measurement, we mainly focus on retrieving complete data, so called as imputation. Also, we adapt the imputation method to missingness varying with measurement policy. However, learning measurement policy and imputation requires complete data which is impossible to be observed, unfortunately. To tack…
Australian National University（澳大利亚国立大学）；Data61, CSIRO（澳大利亚联邦科学与工业研究组织Data61）
This paper tackles the problem of parts-aware point cloud generation. Unlike existing works which require the point cloud to be segmented into parts a priori, our parts-aware editing and generation are performed in an unsupervised manner. We achieve this with a simple modification of the Variational Auto-Encoder which yields a joint model of the point cloud itself along with a schematic representation of it as a combination of shape primitives. In particular, we introduce a latent representation of the point cloud which can be decomposed into a disentangled representation for each part of the …
JointDiff: Bridging Continuous and Discrete in Multi-Agent Trajectory Generation
Kognia Sports Intelligence（Kognia体育智能）；Visual Intelligence for Transportation, EPFL（交通视觉智能，EPFL）；Institut de Robòtica i Informàtica Industrial, CSIC-UPC（机器人与信息工业研究所，CSIC-UPC）
ControlRadio: Prompt-Driven Controllable Diffusion for Cross-Modal Radio Map Generation
Pengcheng Laboratory（鹏城实验室）；South China University of Technology（华南理工大学）；Peking University（北京大学）；Huazhong University of Science and Technology（华中科技大学）；Harbin Institute of Technology, Shenzhen（哈尔滨工业大学（深圳））
The detection of human body and its related parts (e.g., face, head or hands) have been intensively studied and greatly improved since the breakthrough of deep CNNs. However, most of these detectors are trained independently, making it a challenging task to associate detected body parts with people. This paper focuses on the problem of joint detection of human body and its corresponding parts. Specifically, we propose a novel extended object representation that integrates the center location offsets of body or its parts, and construct a dense single-stage anchor-based Body-Part Joint Detector …
Shanghai Jiao Tong University（上海交通大学）；University of Science and Technology of China（中国科学技术大学）；Zhangjiang Laboratory（张江实验室）；Microsoft Research Asia（微软亚洲研究院）
In contrast to the traditional avatar creation pipeline which is a costly process, contemporary generative approaches directly learn the data distribution from photographs. While plenty of works extend unconditional generative models and achieve some levels of controllability, it is still challenging to ensure multi-view consistency, especially in large poses. In this work, we propose a network that generates 3D-aware portraits while being controllable according to semantic parameters regarding pose, identity, expression and illumination. Our network uses neural scene representation to model 3…
University of Modena and Reggio Emilia（摩德纳和雷焦艾米利亚大学）
Current captioning approaches can describe images using black-box architectures whose behavior is hardly controllable and explainable from the exterior. As an image can be described in infinite ways depending on the goal and the context at hand, a higher degree of controllability is needed to apply captioning algorithms in complex scenarios. In this paper, we introduce a novel framework for image captioning which can generate diverse descriptions by allowing both grounding and controllability. Given a control signal in the form of a sequence or set of image regions, we generate the correspondi…
CLIP-PAE: Projection-Augmentation Embedding to Extract Relevant Features for a Disentangled, Interpretable, and Controllable Text-Guided Face Manipulation
Accurate 3D hand pose estimation plays an important role in Human Machine Interaction (HMI). In the reality of HMI, joints in fingers stretching out, especially corresponding fingertips, are much more important than other joints. We propose a novel method to refine stretching-out finger joint locations after obtaining rough hand pose estimation. It first detects which fingers are stretching out, then neighbor pixels of certain joint vote for its new location based on random forests. The algorithm is tested on two public datasets: MSRA15 and ICVL. After the refinement stage of stretching-out fi…
