paper-with-me

홈 › Papers

ObjectAdd: Adding Objects into Image via a Training-Free Diffusion Modification Fashion

2024-04-26 · Ziyue Zhang, Mingbao Lin, Rongrong Ji

We introduce ObjectAdd, a training-free diffusion modification method to add user-expected objects into user-specified area. The motive of ObjectAdd stems from: first, describing everything in one prompt can be difficult, and second, users often need to add objects into the generated image. To accommodate with real world, our ObjectAdd maintains accurate image consistency after adding objects with technical innovations in: (1) embedding-level concatenation to ensure correct text embedding coalesce; (2) object-driven layout control with latent and attention injection to ensure objects accessing user-specified area; (3) prompted image inpainting in an attention refocusing & object expansion fashion to ensure rest of the image stays the same. With a text-prompted image, our ObjectAdd allows users to specify a box and an object, and achieves: (1) adding object inside the box area; (2) exact content outside the box area; (3) flawless fusion between the two areas

📄 PDF Abstract BibTeX arXiv:2404.17230

Code (1)

potato-kitty/objectadd 공식 구현 pytorch

Tasks

Image InpaintingObject

Methods 이 논문이 사용한 방법론

Inpainting Train a convolutional neural network to generate the contents of an arbitrary image region conditioned on its surroundings.
Diffusion Diffusion models generate samples by gradually removing noise from a signal, and their training objective can be expressed as a reweighted variational lower-bound…

Similar Papers 제목 키워드 기반

Paint by Inpaint: Learning to Add Image Objects by Removing Them First

2024-04-28 · CVPR 2025 1 · Navve Wasserman, Noam Rotstein, Roy Ganz, Ron Kimmel

Image editing has advanced significantly with the introduction of text-conditioned diffusion models. Despite this progress, seamlessly adding objects to images based on textual instructions without requiring user-provide…

Image InpaintingLanguage ModelingLanguage ModellingLarge Language Model+3

AI-Driven Stylization of 3D Environments

2024-11-09 · Yuanbo Chen, Yixiao Kang, Yukun Song, Cyrus Vachha 외

In this system, we discuss methods to stylize a scene of 3D primitive objects into a higher fidelity 3D scene using novel 3D representations like NeRFs and 3D Gaussian Splatting. Our approach leverages existing image sty…

Image StylizationImage to 3D

Hierarchical Randomized Smoothing

2023-10-24 · NeurIPS 2023 11 · Yan Scholten, Jan Schuchardt, Aleksandar Bojchevski, Stephan Günnemann

Real-world data is complex and often consists of objects that can be decomposed into multiple entities (e.g. images into pixels, graphs into interconnected nodes). Randomized smoothing is a powerful framework for making …

Node Classification

LoCo: Locally Constrained Training-Free Layout-to-Image Synthesis

2023-11-21 · Peiang Zhao, Han Li, Ruiyang Jin, S. Kevin Zhou

Recent text-to-image diffusion models have reached an unprecedented level in generating high-quality images. However, their exclusive reliance on textual prompts often falls short in precise control of image compositions…

Image Generation

Instructive3D: Editing Large Reconstruction Models with Text Instructions

2025-01-08 · Kunal Kathare, Ankit Dhiman, K Vikas Gowda, Siddharth Aravindan 외

Transformer based methods have enabled users to create, modify, and comprehend text and image data. Recently proposed Large Reconstruction Models (LRMs) further extend this by providing the ability to generate high-quali…