MagicID: Flexible ID Fidelity Generation System

• URL: http://arxiv.org/abs/2408.09248v2
• Date: Tue, 20 Aug 2024 14:39:46 GMT
• Title: MagicID: Flexible ID Fidelity Generation System
• Authors: Zhaoli Deng, Wen Liu, Fanyi Wang, Junkang Zhang, Fan Chen, Meng Zhang, Wendong Zhang, Zhenpeng Mi,
• Abstract summary: Current methods face challenges in generating high-fidelity portrait results when faces occupy a small portion of the image with a low resolution. We propose a systematic solution called MagicID, based on a self-constructed million-level multi-modal dataset named IDZoom. MagicID consists of Multi-Mode Fusion training strategy (MMF) and DDIM Inversion based ID Restoration inference framework (DIIR)
• Score: 11.002947043723617
• License: http://creativecommons.org/licenses/by-nc-sa/4.0/
• Abstract: Portrait Fidelity Generation is a prominent research area in generative models, with a primary focus on enhancing both controllability and fidelity. Current methods face challenges in generating high-fidelity portrait results when faces occupy a small portion of the image with a low resolution, especially in multi-person group photo settings. To tackle these issues, we propose a systematic solution called MagicID, based on a self-constructed million-level multi-modal dataset named IDZoom. MagicID consists of Multi-Mode Fusion training strategy (MMF) and DDIM Inversion based ID Restoration inference framework (DIIR). During training, MMF iteratively uses the skeleton and landmark modalities from IDZoom as conditional guidance. By introducing the Clone Face Tuning in training stage and Mask Guided Multi-ID Cross Attention (MGMICA) in inference stage, explicit constraints on face positional features are achieved for multi-ID group photo generation. The DIIR aims to address the issue of artifacts. The DDIM Inversion is used in conjunction with face landmarks, global and local face features to achieve face restoration while keeping the background unchanged. Additionally, DIIR is plug-and-play and can be applied to any diffusion-based portrait generation method. To validate the effectiveness of MagicID, we conducted extensive comparative and ablation experiments. The experimental results demonstrate that MagicID has significant advantages in both subjective and objective metrics, and achieves controllable generation in multi-person scenarios.

Related papers

• Large Language Models for Multimodal Deformable Image Registration [50.91473745610945]
  We propose a novel coarse-to-fine MDIR framework,LLM-Morph, for aligning the deep features from different modal medical images. Specifically, we first utilize a CNN encoder to extract deep visual features from cross-modal image pairs, then we use the first adapter to adjust these tokens, and use LoRA in pre-trained LLMs to fine-tune their weights. Third, for the alignment of tokens, we utilize other four adapters to transform the LLM-encoded tokens into multi-scale visual features, generating multi-scale deformation fields and facilitating the coarse-to-fine MDIR task
  arXiv  Detail & Related papers  (2024-08-20T09:58:30Z)
• 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)
• InstantFamily: Masked Attention for Zero-shot Multi-ID Image Generation [0.0]
  "InstantFamily" is an approach that employs a novel cross-attention mechanism and a multimodal embedding stack to achieve zero-shot multi-ID image generation. Our method effectively preserves ID as it utilizes global and local features from a pre-trained face recognition model integrated with text conditions.
  arXiv  Detail & Related papers  (2024-04-30T10:16:21Z)
• ConsistentID: Portrait Generation with Multimodal Fine-Grained Identity Preserving [66.09976326184066]
  ConsistentID is an innovative method crafted for diverseidentity-preserving portrait generation under fine-grained multimodal facial prompts. We present a fine-grained portrait dataset, FGID, with over 500,000 facial images, offering greater diversity and comprehensiveness than existing public facial datasets.
  arXiv  Detail & Related papers  (2024-04-25T17:23:43Z)
• Magic Tokens: Select Diverse Tokens for Multi-modal Object Re-Identification [64.36210786350568]
  We propose a novel learning framework named textbfEDITOR to select diverse tokens from vision Transformers for multi-modal object ReID. Our framework can generate more discriminative features for multi-modal object ReID.
  arXiv  Detail & Related papers  (2024-03-15T12:44:35Z)
• Hybrid-Supervised Dual-Search: Leveraging Automatic Learning for Loss-free Multi-Exposure Image Fusion [60.221404321514086]
  Multi-exposure image fusion (MEF) has emerged as a prominent solution to address the limitations of digital imaging in representing varied exposure levels. This paper presents a Hybrid-Supervised Dual-Search approach for MEF, dubbed HSDS-MEF, which introduces a bi-level optimization search scheme for automatic design of both network structures and loss functions.
  arXiv  Detail & Related papers  (2023-09-03T08:07:26Z)
• Learning Progressive Modality-shared Transformers for Effective Visible-Infrared Person Re-identification [27.75907274034702]
  We propose a novel deep learning framework named Progressive Modality-shared Transformer (PMT) for effective VI-ReID. To reduce the negative effect of modality gaps, we first take the gray-scale images as an auxiliary modality and propose a progressive learning strategy. To cope with the problem of large intra-class differences and small inter-class differences, we propose a Discriminative Center Loss.
  arXiv  Detail & Related papers  (2022-12-01T02:20:16Z)
• Efficient and Accurate Multi-scale Topological Network for Single Image Dehazing [31.543771270803056]
  In this paper, we pay attention to the feature extraction and utilization of the input image itself. We propose a Multi-scale Topological Network (MSTN) to fully explore the features at different scales. Meanwhile, we design a Multi-scale Feature Fusion Module (MFFM) and an Adaptive Feature Selection Module (AFSM) to achieve the selection and fusion of features at different scales.
  arXiv  Detail & Related papers  (2021-02-24T08:53:14Z)
• DCDLearn: Multi-order Deep Cross-distance Learning for Vehicle Re-Identification [22.547915009758256]
  This paper formulates a multi-order deep cross-distance learning model for vehicle re-identification. One-view CycleGAN model is developed to alleviate exhaustive and enumerative cross-camera matching problem. Experiments on three vehicle Re-ID datasets demonstrate that the proposed method achieves significant improvement over the state-of-the-arts.
  arXiv  Detail & Related papers  (2020-03-25T10:46:54Z)
• Cross-Resolution Adversarial Dual Network for Person Re-Identification and Beyond [59.149653740463435]
  Person re-identification (re-ID) aims at matching images of the same person across camera views. Due to varying distances between cameras and persons of interest, resolution mismatch can be expected. We propose a novel generative adversarial network to address cross-resolution person re-ID.
  arXiv  Detail & Related papers  (2020-02-19T07:21:38Z)

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.