RealCustom++: Representing Images as Real-Word for Real-Time Customization

• URL: http://arxiv.org/abs/2408.09744v1
• Date: Mon, 19 Aug 2024 07:15:44 GMT
• Title: RealCustom++: Representing Images as Real-Word for Real-Time Customization
• Authors: Zhendong Mao, Mengqi Huang, Fei Ding, Mingcong Liu, Qian He, Xiaojun Chang, Yongdong Zhang,
• Abstract summary: Text-to-image customization aims to synthesize new images that align with both text semantics and subject appearance. Existing works follow the pseudo-word paradigm, which involves representing given subjects as pseudo-words. We propose a novel real-words paradigm termed RealCustom++ that instead represents subjects as non-conflict real words.
• Score: 80.04828124070418
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Text-to-image customization, which takes given texts and images depicting given subjects as inputs, aims to synthesize new images that align with both text semantics and subject appearance. This task provides precise control over details that text alone cannot capture and is fundamental for various real-world applications, garnering significant interest from academia and industry. Existing works follow the pseudo-word paradigm, which involves representing given subjects as pseudo-words and combining them with given texts to collectively guide the generation. However, the inherent conflict and entanglement between the pseudo-words and texts result in a dual-optimum paradox, where subject similarity and text controllability cannot be optimal simultaneously. We propose a novel real-words paradigm termed RealCustom++ that instead represents subjects as non-conflict real words, thereby disentangling subject similarity from text controllability and allowing both to be optimized simultaneously. Specifically, RealCustom++ introduces a novel "train-inference" decoupled framework: (1) During training, RealCustom++ learns the alignment between vision conditions and all real words in the text, ensuring high subject-similarity generation in open domains. This is achieved by the cross-layer cross-scale projector to robustly and finely extract subject features, and a curriculum training recipe that adapts the generated subject to diverse poses and sizes. (2) During inference, leveraging the learned general alignment, an adaptive mask guidance is proposed to only customize the generation of the specific target real word, keeping other subject-irrelevant regions uncontaminated to ensure high text-controllability in real-time.

Related papers

• Image-Text Co-Decomposition for Text-Supervised Semantic Segmentation [28.24883865053459]
  This paper aims to learn a model capable of segmenting arbitrary visual concepts within images by using only image-text pairs without dense annotations. Existing methods have demonstrated that contrastive learning on image-text pairs effectively aligns visual segments with the meanings of texts. A text often consists of multiple semantic concepts, whereas semantic segmentation strives to create semantically homogeneous segments.
  arXiv  Detail & Related papers  (2024-04-05T17:25:17Z)
• RealCustom: Narrowing Real Text Word for Real-Time Open-Domain Text-to-Image Customization [57.86083349873154]
  Text-to-image customization aims to synthesize text-driven images for the given subjects. Existing works follow the pseudo-word paradigm, i.e., represent the given subjects as pseudo-words and then compose them with the given text. We present RealCustom that, for the first time, disentangles similarity from controllability by precisely limiting subject influence to relevant parts only.
  arXiv  Detail & Related papers  (2024-03-01T12:12:09Z)
• Training-Free Consistent Text-to-Image Generation [80.4814768762066]
  Text-to-image models can portray the same subject across diverse prompts. Existing approaches fine-tune the model to teach it new words that describe specific user-provided subjects. We present ConsiStory, a training-free approach that enables consistent subject generation by sharing the internal activations of the pretrained model.
  arXiv  Detail & Related papers  (2024-02-05T18:42:34Z)
• Unleashing the Imagination of Text: A Novel Framework for Text-to-image Person Retrieval via Exploring the Power of Words [0.951828574518325]
  We propose a novel framework to explore the power of words in sentences. The framework employs the pre-trained full CLIP model as a dual encoder for the images and texts. We introduce a cross-modal triplet loss tailored for handling hard samples, enhancing the model's ability to distinguish minor differences.
  arXiv  Detail & Related papers  (2023-07-18T08:23:46Z)
• Plug-and-Play Diffusion Features for Text-Driven Image-to-Image Translation [10.39028769374367]
  We present a new framework that takes text-to-image synthesis to the realm of image-to-image translation. Our method harnesses the power of a pre-trained text-to-image diffusion model to generate a new image that complies with the target text.
  arXiv  Detail & Related papers  (2022-11-22T20:39:18Z)
• Fine-Grained Semantically Aligned Vision-Language Pre-Training [151.7372197904064]
  Large-scale vision-language pre-training has shown impressive advances in a wide range of downstream tasks. Existing methods mainly model the cross-modal alignment by the similarity of the global representations of images and texts. We introduce LO, a fine-grained semantically aLigned visiOn-langUage PrE-training framework, which learns fine-grained semantic alignment from the novel perspective of game-theoretic interactions.
  arXiv  Detail & Related papers  (2022-08-04T07:51:48Z)
• CRIS: CLIP-Driven Referring Image Segmentation [71.56466057776086]
  We propose an end-to-end CLIP-Driven Referring Image framework (CRIS) CRIS resorts to vision-language decoding and contrastive learning for achieving the text-to-pixel alignment. Our proposed framework significantly outperforms the state-of-the-art performance without any post-processing.
  arXiv  Detail & Related papers  (2021-11-30T07:29:08Z)
• FILIP: Fine-grained Interactive Language-Image Pre-Training [106.19474076935363]
  Fine-grained Interactive Language-Image Pre-training achieves finer-level alignment through a cross-modal late interaction mechanism. We construct a new large-scale image-text pair dataset called FILIP300M for pre-training. Experiments show that FILIP achieves state-of-the-art performance on multiple downstream vision-language tasks.
  arXiv  Detail & Related papers  (2021-11-09T17:15:38Z)

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.