Related papers: Towards Design Compositing
Vector graphics are an industry-standard way to represent and share visual designs. Designers frequently source and incorporate styles from existing designs into their own work. Unfortunately, popular design tools aren't well suited for…
Prompting is the primary way to utilize the multitask capabilities of language models (LMs), but prompts occupy valuable space in the input context window, and repeatedly encoding the same prompt is computationally inefficient. Finetuning…
We present an empirical validation of the directional non-commutative monoidal embedding framework recently introduced in prior work~\cite{Godavarti2025monoidal}. This framework defines learnable compositional embeddings using distinct…
Subject-driven text-to-image generation still struggles to preserve high-frequency identity details such as logos, patterns, and text. Existing methods typically operate directly in RGB space, which often leads to detail degradation under…
Text-to-3D generation from a single-view image is a popular but challenging task in 3D vision. Although numerous methods have been proposed, existing works still suffer from the inconsistency issues, including 1) semantic inconsistency, 2)…
The graph convolutional network (GCN) is a go-to solution for machine learning on graphs, but its training is notoriously difficult to scale both in terms of graph size and the number of model parameters. Although some work has explored…
Current image generation and editing methods primarily process textual prompts as direct inputs without reasoning about visual composition and explicit operations. We present Generation Chain-of-Thought (GoT), a novel paradigm that enables…
Recent advances in generative modeling and tokenization have driven significant progress in text-to-motion generation, leading to enhanced quality and realism in generated motions. However, effectively leveraging textual information for…
Multiple-view visualization (MV) is a layout design technique often employed to help users see a large number of data attributes and values in a single cohesive representation. Because of its generalizability, the MV design has been widely…
Generative models have made it possible to synthesize highly realistic images, potentially providing an abundant data source for training machine learning models. Despite the advantages of these synthesizable data sources, the…
Image composition targets at synthesizing a realistic composite image from a pair of foreground and background images. Recently, generative composition methods are built on large pretrained diffusion models to generate composite images,…
Diffusion models excel at text-to-image generation, especially in subject-driven generation for personalized images. However, existing methods are inefficient due to the subject-specific fine-tuning, which is computationally intensive and…
We consider the cross-modal task of producing color representations for text phrases. Motivated by the fact that a significant fraction of user queries on an image search engine follow an (attribute, object) structure, we propose a…
In the text-to-image generation field, recent remarkable progress in Stable Diffusion makes it possible to generate rich kinds of novel photorealistic images. However, current models still face misalignment issues (e.g., problematic spatial…
Creating visually appealing composites requires optimizing both text and background for compatibility. Previous methods have focused on simple design strategies, such as changing text color or adding background shapes for contrast. These…
We offer a novel approach to image composition, which integrates multiple input images into a single, coherent image. Rather than concentrating on specific use cases such as appearance editing (image harmonization) or semantic editing…
Establishing accurate 3D correspondences between shapes stands as a pivotal challenge with profound implications for computer vision and robotics. However, existing self-supervised methods for this problem assume perfect input shape…
In the field of vision-language contrastive learning, models such as CLIP capitalize on matched image-caption pairs as positive examples and leverage within-batch non-matching pairs as negatives. This approach has led to remarkable outcomes…
Perceptually Aligned Gradients (PAG) refer to an intriguing property observed in robust image classification models, wherein their input gradients align with human perception and pose semantic meanings. While this phenomenon has gained…
Recent advances in generative modeling, namely Diffusion models, have revolutionized generative modeling, enabling high-quality image generation tailored to user needs. This paper proposes a framework for the generative design of structural…