Related papers: InsertDiffusion: Identity Preserving Visualization…

Diffusion Transformers (DiTs) excel at generation, but their global self-attention makes controllable, reference-image-based editing a distinct challenge. Unlike U-Nets, naively injecting local appearance into a DiT can disrupt its holistic…

Diffusion models have emerged as frontrunners in text-to-image generation, but their fixed image resolution during training often leads to challenges in high-resolution image generation, such as semantic deviations and object replication.…

Reference-based object composition involves integrating foreground reference image with background scene to produce harmonious fused image. This task becomes particularly challenging in cross-domain scenarios, where models must balance…

We propose Context Diffusion, a diffusion-based framework that enables image generation models to learn from visual examples presented in context. Recent work tackles such in-context learning for image generation, where a query image is…

Stable Diffusion has advanced text-to-image synthesis, but training models to generate images with accurate object quantity is still difficult due to the high computational cost and the challenge of teaching models the abstract concept of…

Diffusion models have become central to various image editing tasks, yet they often fail to fully adhere to physical laws, particularly with effects like shadows, reflections, and occlusions. In this work, we address the challenge of…

Image-based fashion design with AI techniques has attracted increasing attention in recent years. We focus on a new fashion design task, where we aim to transfer a reference appearance image onto a clothing image while preserving the…

Video inpainting is the task of filling a region in a video in a visually convincing manner. It is very challenging due to the high dimensionality of the data and the temporal consistency required for obtaining convincing results. Recently,…

Diffusion models currently achieve state-of-the-art performance for both conditional and unconditional image generation. However, so far, image diffusion models do not support tasks required for 3D understanding, such as view-consistent 3D…

Despite the impressive generative capabilities of diffusion models, existing diffusion model-based style transfer methods require inference-stage optimization (e.g. fine-tuning or textual inversion of style) which is time-consuming, or…

In computer vision, it is well-known that a lack of data diversity will impair model performance. In this study, we address the challenges of enhancing the dataset diversity problem in order to benefit various downstream tasks such as…

Recent advancements in text-to-image diffusion models have significantly transformed visual content generation, yet their application in specialized fields such as interior design remains underexplored. In this paper, we present…

Robots operating in human environments must be able to rearrange objects into semantically-meaningful configurations, even if these objects are previously unseen. In this work, we focus on the problem of building physically-valid structures…

Match-cuts are powerful cinematic tools that create seamless transitions between scenes, delivering strong visual and metaphorical connections. However, crafting match-cuts is a challenging, resource-intensive process requiring deliberate…

Large-scale generative models, such as text-to-image diffusion models, have garnered widespread attention across diverse domains due to their creative and high-fidelity image generation. Nonetheless, existing large-scale diffusion models…

Multiview diffusion models have rapidly emerged as a powerful tool for content creation with spatial consistency across viewpoints, offering rich visual realism without requiring explicit geometry and appearance representation. However,…

As online shopping is growing, the ability for buyers to virtually visualize products in their settings-a phenomenon we define as "Virtual Try-All"-has become crucial. Recent diffusion models inherently contain a world model, rendering them…

Text-to-image diffusion models have attracted considerable interest due to their wide applicability across diverse fields. However, challenges persist in creating controllable models for personalized object generation. In this paper, we…

Generating high-quality 3D objects from textual descriptions remains a challenging problem due to computational cost, the scarcity of 3D data, and complex 3D representations. We introduce Geometry Image Diffusion (GIMDiffusion), a novel…

In this paper, we present a novel paradigm to enhance the ability of object detector, e.g., expanding categories or improving detection performance, by training on synthetic dataset generated from diffusion models. Specifically, we…