We present DINAR, an approach for creating realistic rigged fullbody avatars from single RGB images. Similarly to previous works, our method uses neural textures combined with the SMPL-X body model to achieve photo-realistic quality of avatars while keeping them easy to animate and fast to infer. To restore the texture, we use a latent diffusion model and show how such model can be trained in the neural texture space. The use of the diffusion model allows us to realistically reconstruct large unseen regions such as the back of a person given the frontal view. The models in our pipeline are trained using 2D images and videos only. In the experiments, our approach achieves state-of-the-art rendering quality and good generalization to new poses and viewpoints. In particular, the approach improves state-of-the-art on the SnapshotPeople public benchmark.
相關內容
ACM/IEEE第23屆模型驅動工程語言和系統國際會議，是模型驅動軟件和系統工程的首要會議系列，由ACM-SIGSOFT和IEEE-TCSE支持組織。自1998年以來，模型涵蓋了建模的各個方面，從語言和方法到工具和應用程序。模特的參加者來自不同的背景，包括研究人員、學者、工程師和工業專業人士。MODELS 2019是一個論壇，參與者可以圍繞建模和模型驅動的軟件和系統交流前沿研究成果和創新實踐經驗。今年的版本將為建模社區提供進一步推進建模基礎的機會，并在網絡物理系統、嵌入式系統、社會技術系統、云計算、大數據、機器學習、安全、開源等新興領域提出建模的創新應用以及可持續性。
官網鏈接： ·
MoDELS
·
Processing（編程語言）
·
Guidance
·
Performer
·
Large-scale text-to-video diffusion models have demonstrated an exceptional ability to synthesize diverse videos. However, due to the lack of extensive text-to-video datasets and the necessary computational resources for training, directly applying these models for video stylization remains difficult. Also, given that the noise addition process on the input content is random and destructive, fulfilling the style transfer task's content preservation criteria is challenging. This paper proposes a zero-shot video stylization method named Style-A-Video, which utilizes a generative pre-trained transformer with an image latent diffusion model to achieve a concise text-controlled video stylization. We improve the guidance condition in the denoising process, establishing a balance between artistic expression and structure preservation. Furthermore, to decrease inter-frame flicker and avoid the formation of additional artifacts, we employ a sampling optimization and a temporal consistency module. Extensive experiments show that we can attain superior content preservation and stylistic performance while incurring less consumption than previous solutions. Code will be available at //github.com/haha-lisa/Style-A-Video.
Self-evolving networks (SENs) are emerging technologies that dynamically and autonomously adapt and optimize their performance and behaviour based on changing conditions and evolving requirements. With the advent of fifth-generation (5G) wireless technologies and the resurgence of machine learning, SENs are expected to become a critical component of future wireless networks. In particular, integrated vertical heterogeneous network (VHetNet) architectures, which enable dynamic, three-dimensional (3D), and agile topologies, are likely to form a key foundation for SENs. However, the distributed multi-level computational and communication structure and the fully dynamic nature of self-evolving integrated VHetNets (SEI-VHetNets) necessitate the deployment of an enhanced distributed learning and computing mechanism to enable full integration and coordination. To address this need, we propose a novel learning technique, multi-tier hierarchical federated learning (MT-HFL), based on hierarchical federated learning (HFL) that enables full integration and coordination across vertical tiers. Through MT-HFL, SEI-VHetNets can learn and adapt to dynamic network conditions, optimize resource allocation, and enhance user experience in a real-time, scalable, and accurate manner while preserving user privacy. This paper presents the key characteristics and challenges of SEI-VHetNets and discusses how MT-HFL addresses them. We also discuss potential use cases and present a case study demonstrating the advantages of MT-HFL over conventional terrestrial HFL approaches.
We propose a novel pipeline for the generation of synthetic images via Denoising Diffusion Probabilistic Models (DDPMs) guided by cardiac ultrasound semantic label maps. We show that these synthetic images can serve as a viable substitute for real data in the training of deep-learning models for medical image analysis tasks such as image segmentation. To demonstrate the effectiveness of this approach, we generated synthetic 2D echocardiography images and trained a neural network for segmentation of the left ventricle and left atrium. The performance of the network trained on exclusively synthetic images was evaluated on an unseen dataset of real images and yielded mean Dice scores of 88.5 $\pm 6.0$ , 92.3 $\pm 3.9$, 86.3 $\pm 10.7$ \% for left ventricular endocardial, epicardial and left atrial segmentation respectively. This represents an increase of $9.09$, $3.7$ and $15.0$ \% in Dice scores compared to the previous state-of-the-art. The proposed pipeline has the potential for application to a wide range of other tasks across various medical imaging modalities.
Neural Architecture Search (NAS) has emerged as one of the effective methods to design the optimal neural network architecture automatically. Although neural architectures have achieved human-level performances in several tasks, few of them are obtained from the NAS method. The main reason is the huge search space of neural architectures, making NAS algorithms inefficient. This work presents a novel architecture search algorithm, called GPT-NAS, that optimizes neural architectures by Generative Pre-Trained (GPT) model. In GPT-NAS, we assume that a generative model pre-trained on a large-scale corpus could learn the fundamental law of building neural architectures. Therefore, GPT-NAS leverages the generative pre-trained (GPT) model to propose reasonable architecture components given the basic one. Such an approach can largely reduce the search space by introducing prior knowledge in the search process. Extensive experimental results show that our GPT-NAS method significantly outperforms seven manually designed neural architectures and thirteen architectures provided by competing NAS methods. In addition, our ablation study indicates that the proposed algorithm improves the performance of finely tuned neural architectures by up to about 12% compared to those without GPT, further demonstrating its effectiveness in searching neural architectures.
Over the past decade, 3D graphics have become highly detailed to mimic the real world, exploding their size and complexity. Certain applications and device constraints necessitate their simplification and/or lossy compression, which can degrade their visual quality. Thus, to ensure the best Quality of Experience (QoE), it is important to evaluate the visual quality to accurately drive the compression and find the right compromise between visual quality and data size. In this work, we focus on subjective and objective quality assessment of textured 3D meshes. We first establish a large-scale dataset, which includes 55 source models quantitatively characterized in terms of geometric, color, and semantic complexity, and corrupted by combinations of 5 types of compression-based distortions applied on the geometry, texture mapping and texture image of the meshes. This dataset contains over 343k distorted stimuli. We propose an approach to select a challenging subset of 3000 stimuli for which we collected 148929 quality judgments from over 4500 participants in a large-scale crowdsourced subjective experiment. Leveraging our subject-rated dataset, a learning-based quality metric for 3D graphics was proposed. Our metric demonstrates state-of-the-art results on our dataset of textured meshes and on a dataset of distorted meshes with vertex colors. Finally, we present an application of our metric and dataset to explore the influence of distortion interactions and content characteristics on the perceived quality of compressed textured meshes.
We present AvatarReX, a new method for learning NeRF-based full-body avatars from video data. The learnt avatar not only provides expressive control of the body, hands and the face together, but also supports real-time animation and rendering. To this end, we propose a compositional avatar representation, where the body, hands and the face are separately modeled in a way that the structural prior from parametric mesh templates is properly utilized without compromising representation flexibility. Furthermore, we disentangle the geometry and appearance for each part. With these technical designs, we propose a dedicated deferred rendering pipeline, which can be executed in real-time framerate to synthesize high-quality free-view images. The disentanglement of geometry and appearance also allows us to design a two-pass training strategy that combines volume rendering and surface rendering for network training. In this way, patch-level supervision can be applied to force the network to learn sharp appearance details on the basis of geometry estimation. Overall, our method enables automatic construction of expressive full-body avatars with real-time rendering capability, and can generate photo-realistic images with dynamic details for novel body motions and facial expressions.
Posing high-contact interactions is challenging and time-consuming, with hand-object interactions being especially difficult due to the large number of degrees of freedom (DOF) of the hand and the fact that humans are experts at judging hand poses. This paper addresses this challenge by elevating contact areas to first-class primitives. We provide \textit{end-to-end art-directable} (EAD) tools to model interactions based on contact areas, directly manipulate contact areas, and compute corresponding poses automatically. To make these operations intuitive and fast, we present a novel axis-based contact model that supports real-time approximately isometry-preserving operations on triangulated surfaces, permits movement between surfaces, and is both robust and scalable to large areas. We show that use of our contact model facilitates high quality posing even for unconstrained, high-DOF custom rigs intended for traditional keyframe-based animation pipelines. We additionally evaluate our approach with comparisons to prior art, ablation studies, user studies, qualitative assessments, and extensions to full-body interaction.
Image-based rendering techniques stand at the core of an immersive experience for the user, as they generate novel views given a set of multiple input images. Since they have shown good performance in terms of objective and subjective quality, the research community devotes great effort to their improvement. However, the large volume of data necessary to render at the receiver's side hinders applications in limited bandwidth environments or prevents their employment in real-time applications. We present LeHoPP, a method for input pixel pruning, where we examine the importance of each input pixel concerning the rendered view, and we avoid the use of irrelevant pixels. Even without retraining the image-based rendering network, our approach shows a good trade-off between synthesis quality and pixel rate. When tested in the general neural rendering framework, compared to other pruning baselines, LeHoPP gains between $0.9$ dB and $3.6$ dB on average.
We present DreamPose, a diffusion-based method for generating animated fashion videos from still images. Given an image and a sequence of human body poses, our method synthesizes a video containing both human and fabric motion. To achieve this, we transform a pretrained text-to-image model (Stable Diffusion) into a pose-and-image guided video synthesis model, using a novel finetuning strategy, a set of architectural changes to support the added conditioning signals, and techniques to encourage temporal consistency. We fine-tune on a collection of fashion videos from the UBC Fashion dataset. We evaluate our method on a variety of clothing styles and poses, and demonstrate that our method produces state-of-the-art results on fashion video animation. Video results are available on our project page.
Automatically generating high-quality real world 3D scenes is of enormous interest for applications such as virtual reality and robotics simulation. Towards this goal, we introduce NeuralField-LDM, a generative model capable of synthesizing complex 3D environments. We leverage Latent Diffusion Models that have been successfully utilized for efficient high-quality 2D content creation. We first train a scene auto-encoder to express a set of image and pose pairs as a neural field, represented as density and feature voxel grids that can be projected to produce novel views of the scene. To further compress this representation, we train a latent-autoencoder that maps the voxel grids to a set of latent representations. A hierarchical diffusion model is then fit to the latents to complete the scene generation pipeline. We achieve a substantial improvement over existing state-of-the-art scene generation models. Additionally, we show how NeuralField-LDM can be used for a variety of 3D content creation applications, including conditional scene generation, scene inpainting and scene style manipulation.
小貼士
登錄享
相關主題
注冊地址： 北京市海淀區羊坊店路18號2幢3層301-191