IDEA-Bench: How Far are Generative Models from Professional Designing?
- URL: http://arxiv.org/abs/2412.11767v1
- Date: Mon, 16 Dec 2024 13:39:32 GMT
- Title: IDEA-Bench: How Far are Generative Models from Professional Designing?
- Authors: Chen Liang, Lianghua Huang, Jingwu Fang, Huanzhang Dou, Wei Wang, Zhi-Fan Wu, Yupeng Shi, Junge Zhang, Xin Zhao, Yu Liu,
- Abstract summary: We introduce IDEA-Bench, a benchmark encompassing 100 real-world design tasks.
This includes rendering, visual effects, storyboarding, picture books, fonts, style-based, and identity-preserving generation.
Even the best-performing model only achieves 22.48 on IDEA-Bench, while the best general-purpose model only achieves 6.81.
- Score: 34.00716542613326
- License:
- Abstract: Real-world design tasks - such as picture book creation, film storyboard development using character sets, photo retouching, visual effects, and font transfer - are highly diverse and complex, requiring deep interpretation and extraction of various elements from instructions, descriptions, and reference images. The resulting images often implicitly capture key features from references or user inputs, making it challenging to develop models that can effectively address such varied tasks. While existing visual generative models can produce high-quality images based on prompts, they face significant limitations in professional design scenarios that involve varied forms and multiple inputs and outputs, even when enhanced with adapters like ControlNets and LoRAs. To address this, we introduce IDEA-Bench, a comprehensive benchmark encompassing 100 real-world design tasks, including rendering, visual effects, storyboarding, picture books, fonts, style-based, and identity-preserving generation, with 275 test cases to thoroughly evaluate a model's general-purpose generation capabilities. Notably, even the best-performing model only achieves 22.48 on IDEA-Bench, while the best general-purpose model only achieves 6.81. We provide a detailed analysis of these results, highlighting the inherent challenges and providing actionable directions for improvement. Additionally, we provide a subset of 18 representative tasks equipped with multimodal large language model (MLLM)-based auto-evaluation techniques to facilitate rapid model development and comparison. We releases the benchmark data, evaluation toolkits, and an online leaderboard at https://github.com/ali-vilab/IDEA-Bench, aiming to drive the advancement of generative models toward more versatile and applicable intelligent design systems.
Related papers
- EditAR: Unified Conditional Generation with Autoregressive Models [58.093860528672735]
We propose EditAR, a single unified autoregressive framework for a variety of conditional image generation tasks.
The model takes both images and instructions as inputs, and predicts the edited images tokens in a vanilla next-token paradigm.
We evaluate its effectiveness across diverse tasks on established benchmarks, showing competitive performance to various state-of-the-art task-specific methods.
arXiv Detail & Related papers (2025-01-08T18:59:35Z) - You Only Submit One Image to Find the Most Suitable Generative Model [48.67303250592189]
We propose a novel setting called Generative Model Identification (GMI)
GMI aims to enable the user to identify the most appropriate generative model(s) for the user's requirements efficiently.
arXiv Detail & Related papers (2024-12-16T14:46:57Z) - AnySynth: Harnessing the Power of Image Synthetic Data Generation for Generalized Vision-Language Tasks [23.041812897803034]
We propose Any Synth, a unified framework capable of generating arbitrary type of synthetic data.
We have validated our framework's performance across various tasks, including Few-shot Object Detection, Cross-domain Object Detection, Zero-shot Image Retrieval, and Multi-modal Image Perception and Grounding.
arXiv Detail & Related papers (2024-11-24T04:49:07Z) - ACE: All-round Creator and Editor Following Instructions via Diffusion Transformer [40.32254040909614]
We propose ACE, an All-round Creator and Editor, for visual generation tasks.
We first introduce a unified condition format termed Long-context Condition Unit (LCU)
We then propose a novel Transformer-based diffusion model that uses LCU as input, aiming for joint training across various generation and editing tasks.
arXiv Detail & Related papers (2024-09-30T17:56:27Z) - InstructCV: Instruction-Tuned Text-to-Image Diffusion Models as Vision Generalists [66.85125112199898]
We develop a unified language interface for computer vision tasks that abstracts away task-specific design choices.
Our model, dubbed InstructCV, performs competitively compared to other generalist and task-specific vision models.
arXiv Detail & Related papers (2023-09-30T14:26:43Z) - StableLLaVA: Enhanced Visual Instruction Tuning with Synthesized
Image-Dialogue Data [129.92449761766025]
We propose a novel data collection methodology that synchronously synthesizes images and dialogues for visual instruction tuning.
This approach harnesses the power of generative models, marrying the abilities of ChatGPT and text-to-image generative models.
Our research includes comprehensive experiments conducted on various datasets.
arXiv Detail & Related papers (2023-08-20T12:43:52Z) - GPT4Image: Can Large Pre-trained Models Help Vision Models on Perception
Tasks? [51.22096780511165]
We present a new learning paradigm in which the knowledge extracted from large pre-trained models are utilized to help models like CNN and ViT learn enhanced representations.
We feed detailed descriptions into a pre-trained encoder to extract text embeddings with rich semantic information that encodes the content of images.
arXiv Detail & Related papers (2023-06-01T14:02:45Z) - Advancing Plain Vision Transformer Towards Remote Sensing Foundation
Model [97.9548609175831]
We resort to plain vision transformers with about 100 million parameters and make the first attempt to propose large vision models customized for remote sensing tasks.
Specifically, to handle the large image size and objects of various orientations in RS images, we propose a new rotated varied-size window attention.
Experiments on detection tasks demonstrate the superiority of our model over all state-of-the-art models, achieving 81.16% mAP on the DOTA-V1.0 dataset.
arXiv Detail & Related papers (2022-08-08T09:08:40Z)
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.