通知：联邦节假日调休：哥伦布日 / 原住民日（Columbus Day / Indigenous Peoples' Day），今日（13日）无更新。通知：联邦节假日调休：哥伦布日 / 原住民日（Columbus Day / Indigenous Peoples' Day），今日（13日）无更新。
arXiv 2304.12536cs.CV
探索基于潜在分类器引导的组合视觉生成
Exploring Compositional Visual Generation with Latent Classifier Guidance
University of California, San Diego（加州大学圣地亚哥分校）；The Pennsylvania State University（宾夕法尼亚州立大学）；NEC Laboratories America（NEC美国实验室）；Northwestern University（西北大学）
Changhao Shi, Haomiao Ni, Kai Li, Shaobo Han, Mingfu Liang, Martin Renqiang Min
Diffusion probabilistic models have achieved enormous success in the field of image generation and manipulation. In this paper, we explore a novel paradigm of using the diffusion model and classifier guidance in the latent semantic space for compositional visual tasks. Specifically, we train latent diffusion models and auxiliary latent classifiers to facilitate non-linear navigation of latent representation generation for any pre-trained generative model with a semantic latent space. We demonstrate that such conditional generation achieved by latent classifier guidance provably maximizes a lower bound of the conditional log probability during training. To maintain the original semantics during manipulation, we introduce a new guidance term, which we show is crucial for achieving compositionality. With additional assumptions, we show that the non-linear manipulation reduces to a simple latent arithmetic approach. We show that this paradigm based on latent classifier guidance is agnostic to pre-trained generative models, and present competitive results for both image generation and sequential manipulation of real and synthetic images. Our findings suggest that latent classifier guidance is a promising approach that merits further exploration, even in the presence of other strong competing methods.
Training-free Subject-Enhanced Attention Guidance for Compositional Text-to-image Generation
University of Chinese Academy of Sciences, Beijing, China（中国科学院大学）；Institute of Automation, Chinese Academy of Sciences, Beijing, China（中国科学院自动化研究所）；Kuaishou Technology, Beijing, China（快手科技）
University of California, Santa Barbara（加州大学圣巴巴拉分校）；University of California, Santa Cruz（加州大学圣克鲁兹分校）；Google（谷歌）
Large-scale diffusion models have achieved state-of-the-art results on text-to-image synthesis (T2I) tasks. Despite their ability to generate high-quality yet creative images, we observe that attribution-binding and compositional capabilities are still considered major challenging issues, especially when involving multiple objects. In this work, we improve the compositional skills of T2I models, specifically more accurate attribute binding and better image compositions. To do this, we incorporate linguistic structures with the diffusion guidance process based on the controllable properties of …
ComboVerse: Compositional 3D Assets Creation Using Spatially-Aware Diffusion Guidance
S-Lab, Nanyang Technological University（南洋理工大学S-Lab）；Shanghai Artificial Intelligence Laboratory（上海人工智能实验室）；The Chinese University of Hong Kong（香港中文大学）；The Chinese University of Hong Kong, Shenzhen（香港中文大学（深圳））
Conflict-Aware Additive Guidance for Flow Models under Compositional Rewards
Smart Systems Institute, National University of Singapore, Singapore（新加坡国立大学智能系统研究所）；Faculty of Computing, Harbin Institute of Technology, Harbin, China（哈尔滨工业大学计算机学院）；School of Computing, National University of Singapore, Singapore（新加坡国立大学计算机学院）
Compositional Text-to-Image Generation Via Region-aware Bimodal Direct Preference Optimization
Shanghai Key Lab of Intell. Info. Processing, School of CS, Fudan University（上海智能信息处理关键实验室，复旦大学计算机学院）；Shanghai Collaborative Innovation Center of Intelligent Visual Computing（上海智能视觉计算协同创新中心）
Training-Free Text-to-Image Compositional Food Generation via Prompt Grafting
Elmore Family School of Electrical and Computer Engineering, Purdue University（电气与计算机工程学院，普渡大学）；Department of Systems Design Engineering, University of Waterloo（系统设计工程系，滑铁卢大学）
Language-Grounded Multi-Domain Image Translation via Semantic Difference Guidance
Department of Artificial Intelligence, Chung-Ang University（人工智能系， Chung-Ang 大学）；Hyundai Mobis；Korea Advanced Institute of Science and Technology（韩国科学技术院）
Anguinus Sculpturae: Compositional Synthesis of Peak-Enhancement Breast DCE-MRI Scans
German Cancer Research Center (DKFZ)（德国癌症研究中心）；Heidelberg University（海德堡大学）；HIDSS4Health – Helmholtz Information and Data Science School for Health（HIDSS4Health – 亥姆霍兹健康信息与数据科学学校）；Helmholtz Imaging（亥姆霍兹成像中心）
Despite remarkable success in unpaired image-to-image translation, existing systems still require a large amount of labeled images. This is a bottleneck for their real-world applications; in practice, a model trained on labeled CelebA dataset does not work well for test images from a different distribution -- greatly limiting their application to unlabeled images of a much larger quantity. In this paper, we attempt to alleviate this necessity for labeled data in the facial image translation domain. We aim to explore the degree to which you can discover novel attributes from unlabeled faces and…
CardioComposer: Leveraging Differentiable Geometry for Compositional Control of Anatomical Diffusion Models
Massachusetts Institute of Technology（麻省理工学院）；Brigham and Women’s Hospital（布里奇沃特医院）；American University in Cairo（开罗美国大学）；École Polytechnique Fédérale de Lausanne（洛桑联邦理工学院）
Shanghai Jiao Tong University（上海交通大学）；SenseTime Research（商汤科技研究院）；East China Normal University（华东师范大学）
Prior plays an important role in providing the plausible constraint on human motion. Previous works design motion priors following a variety of paradigms under different circumstances, leading to the lack of versatility. In this paper, we first summarize the indispensable properties of the motion prior, and accordingly, design a framework to learn the versatile motion prior, which models the inherent probability distribution of human motions. Specifically, for efficient prior representation learning, we propose a global orientation normalization to remove redundant environment information in t…
CADKnitter: Compositional CAD Generation from Text and Geometry Guidance
FPT Software AI Center（FPT软件AI中心）；Department of Robotics, Mohamed bin Zayed University of Artificial Intelligence (MBZUAI)（机器人系，Mohamed bin Zayed人工智能大学）；Department of Computer Science, University of Liverpool（计算机科学系，利物浦大学）；Department of Creative Informatics, The University of Tokyo（创意信息学系，东京大学）
RoboFactory: Exploring Embodied Agent Collaboration with Compositional Constraints
The Chinese University of Hong Kong, Shenzhen（香港中文大学（深圳））；Shanghai Artificial Intelligence Laboratory（上海人工智能实验室）；Oxford（牛津大学）；HKU（香港大学）；Sun Yat-sen University（中山大学）；Tongji University（同济大学）；Shanghai Jiao Tong University（上海交通大学）
Exploring Modality Guidance to Enhance VFM-based Feature Fusion for UDA in 3D Semantic Segmentation
Institute of Visual Computing, Graz University of Technology（视觉计算研究所，格拉茨技术大学）；JKU LINZ（JKU林茨）；TU Wien（维也纳技术大学）；IBM Research（IBM研究院）；MIT CSAIL（麻省理工学院计算机科学与人工智能实验室）
