AnyMaker: Zero-shot General Object Customization via Decoupled Dual-Level ID Injection

• URL: http://arxiv.org/abs/2406.11643v3
• Date: Fri, 5 Jul 2024 13:10:51 GMT
• Title: AnyMaker: Zero-shot General Object Customization via Decoupled Dual-Level ID Injection
• Authors: Lingjie Kong, Kai Wu, Xiaobin Hu, Wenhui Han, Jinlong Peng, Chengming Xu, Donghao Luo, Jiangning Zhang, Chengjie Wang, Yanwei Fu,
• Abstract summary: We introduce AnyMaker, a framework capable of generating general objects with high ID fidelity and flexible text editability. The efficacy of AnyMaker stems from its novel general ID extraction, dual-level ID injection, and ID-aware decoupling. To validate our approach and boost the research of general object customization, we create the first large-scale general ID dataset.
• Score: 72.41427550339296
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Text-to-image based object customization, aiming to generate images with the same identity (ID) as objects of interest in accordance with text prompts and reference images, has made significant progress. However, recent customizing research is dominated by specialized tasks, such as human customization or virtual try-on, leaving a gap in general object customization. To this end, we introduce AnyMaker, an innovative zero-shot object customization framework capable of generating general objects with high ID fidelity and flexible text editability. The efficacy of AnyMaker stems from its novel general ID extraction, dual-level ID injection, and ID-aware decoupling. Specifically, the general ID extraction module extracts sufficient ID information with an ensemble of self-supervised models to tackle the diverse customization tasks for general objects. Then, to provide the diffusion UNet with the extracted ID as much while not damaging the text editability in the generation process, we design a global-local dual-level ID injection module, in which the global-level semantic ID is injected into text descriptions while the local-level ID details are injected directly into the model through newly added cross-attention modules. In addition, we propose an ID-aware decoupling module to disentangle ID-related information from non-ID elements in the extracted representations for high-fidelity generation of both identity and text descriptions. To validate our approach and boost the research of general object customization, we create the first large-scale general ID dataset, Multi-Category ID-Consistent (MC-IDC) dataset, with 315k text-image samples and 10k categories. Experiments show that AnyMaker presents remarkable performance in general object customization and outperforms specialized methods in corresponding tasks. Code and dataset will be released soon.

Related papers

• UniPortrait: A Unified Framework for Identity-Preserving Single- and Multi-Human Image Personalization [10.760799194716922]
  UniPortrait is an innovative human image personalization framework that unifies single- and multi-ID customization. UniPortrait consists of only two plug-and-play modules: an ID embedding module and an ID routing module.
  arXiv  Detail & Related papers  (2024-08-12T06:27:29Z)
• Synthesizing Efficient Data with Diffusion Models for Person Re-Identification Pre-Training [51.87027943520492]
  We present a novel paradigm Diffusion-ReID to efficiently augment and generate diverse images based on known identities. Benefiting from our proposed paradigm, we first create a new large-scale person Re-ID dataset Diff-Person, which consists of over 777K images from 5,183 identities.
  arXiv  Detail & Related papers  (2024-06-10T06:26:03Z)
• Infinite-ID: Identity-preserved Personalization via ID-semantics Decoupling Paradigm [31.06269858216316]
  We propose Infinite-ID, an ID-semantics decoupling paradigm for identity-preserved personalization. We introduce an identity-enhanced training, incorporating an additional image cross-attention module to capture sufficient ID information. We also introduce a feature interaction mechanism that combines a mixed attention module with an AdaIN-mean operation to seamlessly merge the two streams.
  arXiv  Detail & Related papers  (2024-03-18T13:39:53Z)
• Magic-Me: Identity-Specific Video Customized Diffusion [72.05925155000165]
  We propose a controllable subject identity controllable video generation framework, termed Video Custom Diffusion (VCD) With a specified identity defined by a few images, VCD reinforces the identity characteristics and injects frame-wise correlation for stable video outputs. We conducted extensive experiments to verify that VCD is able to generate stable videos with better ID over the baselines.
  arXiv  Detail & Related papers  (2024-02-14T18:13:51Z)
• PhotoMaker: Customizing Realistic Human Photos via Stacked ID Embedding [102.07914175196817]
  PhotoMaker is an efficient personalized text-to-image generation method. It encodes an arbitrary number of input ID images into a stack ID embedding for preserving ID information.
  arXiv  Detail & Related papers  (2023-12-07T17:32:29Z)
• Zero-Shot In-Distribution Detection in Multi-Object Settings Using Vision-Language Foundation Models [37.36999826208225]
  In this paper, we propose a novel problem setting called zero-shot in-distribution (ID) detection. We identify images containing ID objects as ID images (even if they contain OOD objects) and images lacking ID objects as OOD images without any training. We present a simple and effective approach, Global-Local Concept Matching, based on both global and local visual-text alignments of CLIP features.
  arXiv  Detail & Related papers  (2023-04-10T11:35:42Z)
• Multi-Stage Spatio-Temporal Aggregation Transformer for Video Person Re-identification [78.08536797239893]
  We propose a novel Multi-Stage Spatial-Temporal Aggregation Transformer (MSTAT) with two novel designed proxy embedding modules. MSTAT consists of three stages to encode the attribute-associated, the identity-associated, and the attribute-identity-associated information from the video clips. We show that MSTAT can achieve state-of-the-art accuracies on various standard benchmarks.
  arXiv  Detail & Related papers  (2023-01-02T05:17:31Z)
• Identity-Aware Multi-Sentence Video Description [105.13845996039277]
  We introduce an auxiliary task of Fill-in the Identity, that aims to predict persons' IDs consistently within a set of clips. One of the key components is a gender-aware textual representation as well an additional gender prediction objective in the main model. Experiments show that our proposed Fill-in the Identity model is superior to several baselines and recent works.
  arXiv  Detail & Related papers  (2020-08-22T09:50:43Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.