TF-TI2I: Training-Free Text-and-Image-to-Image Generation via Multi-Modal Implicit-Context Learning in Text-to-Image Models

Text-and-Image-To-Image (TI2I), an extension of Text-To-Image (T2I), integrates image inputs with textual instructions to enhance image generation. Existing methods often partially utilize image inputs, focusing on specific elements like objects or styles, or they experience a decline in generation quality with complex, multi-image instructions. To overcome these challenges, we introduce Training-Free Text-and-Image-to-Image (TF-TI2I), which adapts cutting-edge T2I models such as SD3 without the need for additional training. Our method capitalizes on the MM-DiT architecture, in which we point out that textual tokens can implicitly learn visual information from vision tokens. We enhance this interaction by extracting a condensed visual representation from reference images, facilitating selective information sharing through Reference Contextual Masking -- this technique confines the usage of contextual tokens to instruction-relevant visual information. Additionally, our Winner-Takes-All module mitigates distribution shifts by prioritizing the most pertinent references for each vision token. Addressing the gap in TI2I evaluation, we also introduce the FG-TI2I Bench, a comprehensive benchmark tailored for TI2I and compatible with existing T2I methods. Our approach shows robust performance across various benchmarks, confirming its effectiveness in handling complex image-generation tasks.

FreeCond: Free Lunch in the Input Conditions of Text-Guided Inpainting

In this study, we aim to determine and solve the deficiency of Stable Diffusion Inpainting (SDI) in following the instruction of both prompt and mask. Due to the training bias from masking, the inpainting quality is hindered when the prompt instruction and image condition are not related. Therefore, we conduct a detailed analysis of the internal representations learned by SDI, focusing on how the mask input influences the cross-attention layer. We observe that adapting text key tokens toward the input mask enables the model to selectively paint within the given area. Leveraging these insights, we propose FreeCond, which adjusts only the input mask condition and image condition. By increasing the latent mask value and modifying the frequency of image condition, we align the cross-attention features with the model's training bias to improve generation quality without additional computation, particularly when user inputs are complicated and deviate from the training setup. Extensive experiments demonstrate that FreeCond can enhance any SDI-based model, e.g., yielding up to a 60% and 58% improvement of SDI and SDXLI in the CLIP score.

Traffic Scene Generation from Natural Language Description for Autonomous Vehicles with Large Language Model

Text-to-scene generation, transforming textual descriptions into detailed scenes, typically relies on generating key scenarios along predetermined paths, constraining environmental diversity and limiting customization flexibility. To address these limitations, we propose a novel text-to-traffic scene framework that leverages a large language model to generate diverse traffic scenarios within the Carla simulator based on natural language descriptions. Users can define specific parameters such as weather conditions, vehicle types, and road signals, while our pipeline can autonomously select the starting point and scenario details, generating scenes from scratch without relying on predetermined locations or trajectories. Furthermore, our framework supports both critical and routine traffic scenarios, enhancing its applicability. Experimental results indicate that our approach promotes diverse agent planning and road selection, enhancing the training of autonomous agents in traffic environments. Notably, our methodology has achieved a 16% reduction in average collision rates. Our work is made publicly available at https://basiclab.github.io/TTSG.

Training-and-prompt-free General Painterly Harmonization Using Image-wise Attention Sharing

Painterly Image Harmonization aims at seamlessly blending disparate visual elements within a single coherent image. However, previous approaches often encounter significant limitations due to training data constraints, the need for time-consuming fine-tuning, or reliance on additional prompts. To surmount these hurdles, we design a Training-and-prompt-Free General Painterly Harmonization method using image-wise attention sharing (TF-GPH), which integrates a novel "share-attention module". This module redefines the traditional self-attention mechanism by allowing for comprehensive image-wise attention, facilitating the use of a state-of-the-art pretrained latent diffusion model without the typical training data limitations. Additionally, we further introduce "similarity reweighting" mechanism enhances performance by effectively harnessing cross-image information, surpassing the capabilities of fine-tuning or prompt-based approaches. At last, we recognize the deficiencies in existing benchmarks and propose the "General Painterly Harmonization Benchmark", which employs range-based evaluation metrics to more accurately reflect real-world application. Extensive experiments demonstrate the superior efficacy of our method across various benchmarks. The code and web demo are available at https://github.com/BlueDyee/TF-GPH.

Vision Transformers: State of the Art and Research Challenges

Transformers have achieved great success in natural language processing. Due to the powerful capability of self-attention mechanism in transformers, researchers develop the vision transformers for a variety of computer vision tasks, such as image recognition, object detection, image segmentation, pose estimation, and 3D reconstruction. This paper presents a comprehensive overview of the literature on different architecture designs and training tricks (including self-supervised learning) for vision transformers. Our goal is to provide a systematic review with the open research opportunities.