UniWorld-V1: High-Resolution Semantic Encoders for Unified Visual Understanding and Generation

• URL: http://arxiv.org/abs/2506.03147v3
• Date: Thu, 05 Jun 2025 16:41:40 GMT
• Title: UniWorld-V1: High-Resolution Semantic Encoders for Unified Visual Understanding and Generation
• Authors: Bin Lin, Zongjian Li, Xinhua Cheng, Yuwei Niu, Yang Ye, Xianyi He, Shenghai Yuan, Wangbo Yu, Shaodong Wang, Yunyang Ge, Yatian Pang, Li Yuan,
• Abstract summary: OpenAI introduced the powerful GPT-4o-Image model, which showcases advanced capabilities in comprehensive image perception and manipulation.<n>Inspired by this insight, we propose UniWorld-V1, a unified generative framework built upon semantic features extracted from powerful large language models.
• Score: 14.95468978198402
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Although existing unified models achieve strong performance in vision-language understanding and text-to-image generation, they remain limited in addressing image perception and manipulation -- capabilities increasingly demanded in practical applications. Recently, OpenAI introduced the powerful GPT-4o-Image model, which showcases advanced capabilities in comprehensive image perception and manipulation, sparking widespread interest. Through carefully designed experiments, we observe that GPT-4o-Image likely relies on semantic encoders rather than VAEs for feature extraction, despite VAEs being commonly regarded as crucial for image manipulation tasks. Inspired by this insight, we propose UniWorld-V1, a unified generative framework built upon semantic features extracted from powerful multimodal large language models and contrastive semantic encoders. Using only 2.7M training data, UniWorld-V1 achieves impressive performance across diverse tasks, including image understanding, generation, manipulation, and perception. We fully open-source the UniWorld-V1 framework, including model weights, training and evaluation scripts, and datasets to promote reproducibility and further research.

Related papers

• Weaving Context Across Images: Improving Vision-Language Models through Focus-Centric Visual Chains [31.828341309787042]
  Vision-language models (VLMs) achieve remarkable success in single-image tasks.<n>Real-world scenarios often involve intricate multi-image inputs, leading to a notable performance decline.<n>We propose Focus-Centric Visual Chain, a novel paradigm that enhances VLMs'perception, comprehension, and reasoning abilities in multi-image scenarios.
  arXiv  Detail & Related papers  (2025-04-28T19:02:18Z)
• Semantics Disentanglement and Composition for Versatile Codec toward both Human-eye Perception and Machine Vision Task [47.7670923159071]
  This study introduces an innovative semantics DISentanglement and COmposition VERsatile (DISCOVER) to simultaneously enhance human-eye perception and machine vision tasks.<n>The approach derives a set of labels per task through multimodal large models, which grounding models are then applied for precise localization, enabling a comprehensive understanding and disentanglement of image components at the encoder side.<n>At the decoding stage, a comprehensive reconstruction of the image is achieved by leveraging these encoded components alongside priors from generative models, thereby optimizing performance for both human visual perception and machine-based analytical tasks.
  arXiv  Detail & Related papers  (2024-12-24T04:32:36Z)
• Lumina-mGPT: Illuminate Flexible Photorealistic Text-to-Image Generation with Multimodal Generative Pretraining [49.04935506942202]
  Lumina-mGPT is a family of multimodal autoregressive models capable of various vision and language tasks.<n>By initializing from multimodal Generative PreTraining (mGPT), we demonstrate that decoder-only Autoregressive (AR) model can achieve image generation performance comparable to modern diffusion models.
  arXiv  Detail & Related papers  (2024-08-05T17:46:53Z)
• INF-LLaVA: Dual-perspective Perception for High-Resolution Multimodal Large Language Model [71.50973774576431]
  We propose a novel MLLM, INF-LLaVA, designed for effective high-resolution image perception. We introduce a Dual-perspective Cropping Module (DCM), which ensures that each sub-image contains continuous details from a local perspective. Second, we introduce Dual-perspective Enhancement Module (DEM) to enable the mutual enhancement of global and local features.
  arXiv  Detail & Related papers  (2024-07-23T06:02:30Z)
• Enhancing Large Vision Language Models with Self-Training on Image Comprehension [131.14381425260706]
  We introduce Self-Training on Image (STIC), which emphasizes a self-training approach specifically for image comprehension. First, the model self-constructs a preference for image descriptions using unlabeled images. To further self-improve reasoning on the extracted visual information, we let the model reuse a small portion of existing instruction-tuning data.
  arXiv  Detail & Related papers  (2024-05-30T05:53:49Z)
• GiT: Towards Generalist Vision Transformer through Universal Language Interface [94.33443158125186]
  This paper proposes a simple, yet effective framework, called GiT, simultaneously applicable for various vision tasks only with a vanilla ViT. GiT is a multi-task visual model, jointly trained across five representative benchmarks without task-specific fine-tuning.
  arXiv  Detail & Related papers  (2024-03-14T13:47:41Z)
• Jack of All Tasks, Master of Many: Designing General-purpose Coarse-to-Fine Vision-Language Model [83.85856356798531]
  VistaLLM is a visual system that addresses coarse- and fine-grained vision-language tasks. It employs a gradient-aware adaptive sampling technique to represent binary segmentation masks as sequences. We also introduce a novel task, AttCoSeg, which boosts the model's reasoning and grounding capability over multiple input images.
  arXiv  Detail & Related papers  (2023-12-19T18:53:01Z)
• General Object Foundation Model for Images and Videos at Scale [99.2806103051613]
  We present GLEE, an object-level foundation model for locating and identifying objects in images and videos. GLEE accomplishes detection, segmentation, tracking, grounding, and identification of arbitrary objects in the open world scenario. We employ an image encoder, text encoder, and visual prompter to handle multi-modal inputs, enabling to simultaneously solve various object-centric downstream tasks.
  arXiv  Detail & Related papers  (2023-12-14T17:26:00Z)
• UniDiff: Advancing Vision-Language Models with Generative and Discriminative Learning [86.91893533388628]
  This paper presents UniDiff, a unified multi-modal model that integrates image-text contrastive learning (ITC), text-conditioned image synthesis learning (IS), and reciprocal semantic consistency modeling (RSC) UniDiff demonstrates versatility in both multi-modal understanding and generative tasks.
  arXiv  Detail & Related papers  (2023-06-01T15:39:38Z)
• GPT4Image: Large Pre-trained Models Help Vision Models Learn Better on Perception Task [47.1857510710807]
  We present a new learning framework, dubbed GPT4Image, where the knowledge of the large pre-trained models are extracted to help CNNs and ViTs learn better representations.<n>We conduct extensive experiments to verify the effectiveness of the proposed algorithm on various visual perception tasks.
  arXiv  Detail & Related papers  (2023-06-01T14:02:45Z)
• The Devil is in the Frequency: Geminated Gestalt Autoencoder for Self-Supervised Visual Pre-Training [13.087987450384036]
  We present a new Masked Image Modeling (MIM), termed Geminated Autoencoder (Ge$2$-AE) for visual pre-training. Specifically, we equip our model with geminated decoders in charge of reconstructing image contents from both pixel and frequency space.
  arXiv  Detail & Related papers  (2022-04-18T09:22:55Z)

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.