Add-it: Training-Free Object Insertion in Images With Pretrained Diffusion Models

• URL: http://arxiv.org/abs/2411.07232v2
• Date: Tue, 12 Nov 2024 07:49:39 GMT
• Title: Add-it: Training-Free Object Insertion in Images With Pretrained Diffusion Models
• Authors: Yoad Tewel, Rinon Gal, Dvir Samuel, Yuval Atzmon, Lior Wolf, Gal Chechik,
• Abstract summary: Add-it is a training-free approach that extends diffusion models' attention mechanisms to incorporate information from three key sources. Our weighted extended-attention mechanism maintains structural consistency and fine details while ensuring natural object placement. Human evaluations show that Add-it is preferred in over 80% of cases.
• Score: 78.90023746996302
• License:
• Abstract: Adding Object into images based on text instructions is a challenging task in semantic image editing, requiring a balance between preserving the original scene and seamlessly integrating the new object in a fitting location. Despite extensive efforts, existing models often struggle with this balance, particularly with finding a natural location for adding an object in complex scenes. We introduce Add-it, a training-free approach that extends diffusion models' attention mechanisms to incorporate information from three key sources: the scene image, the text prompt, and the generated image itself. Our weighted extended-attention mechanism maintains structural consistency and fine details while ensuring natural object placement. Without task-specific fine-tuning, Add-it achieves state-of-the-art results on both real and generated image insertion benchmarks, including our newly constructed "Additing Affordance Benchmark" for evaluating object placement plausibility, outperforming supervised methods. Human evaluations show that Add-it is preferred in over 80% of cases, and it also demonstrates improvements in various automated metrics.

Related papers

• Generative Location Modeling for Spatially Aware Object Insertion [35.62317512925592]
  Generative models have become a powerful tool for image editing tasks, including object insertion. In this paper, we focus on creating a location model dedicated to identifying realistic object locations. Specifically, we train an autoregressive model that generates bounding box coordinates, conditioned on the background image and the desired object class. This formulation allows to effectively handle sparse placement annotations and to incorporate implausible locations into a preference dataset by performing direct preference optimization.
  arXiv  Detail & Related papers  (2024-10-17T14:00:41Z)
• EraseDraw: Learning to Insert Objects by Erasing Them from Images [24.55843674256795]
  Prior works often fail by making global changes to the image, inserting objects in unrealistic spatial locations, and generating inaccurate lighting details. We observe that while state-of-the-art models perform poorly on object insertion, they can remove objects and erase the background in natural images very well. We show compelling results on diverse insertion prompts and images across various domains.
  arXiv  Detail & Related papers  (2024-08-31T18:37:48Z)
• DiffUHaul: A Training-Free Method for Object Dragging in Images [78.93531472479202]
  We propose a training-free method, dubbed DiffUHaul, for the object dragging task. We first apply attention masking in each denoising step to make the generation more disentangled across different objects. In the early denoising steps, we interpolate the attention features between source and target images to smoothly fuse new layouts with the original appearance.
  arXiv  Detail & Related papers  (2024-06-03T17:59:53Z)
• Outline-Guided Object Inpainting with Diffusion Models [11.391452115311798]
  Instance segmentation datasets play a crucial role in training accurate and robust computer vision models. We show how this issue can be mitigated by starting with small annotated instance segmentation datasets and augmenting them to obtain a sizeable annotated dataset. We generate new images using a diffusion-based inpainting model to fill out the masked area with a desired object class by guiding the diffusion through the object outline.
  arXiv  Detail & Related papers  (2024-02-26T09:21:17Z)
• LoCo: Locally Constrained Training-Free Layout-to-Image Synthesis [24.925757148750684]
  We propose a training-free approach for layout-to-image Synthesis that excels in producing high-quality images aligned with both textual prompts and layout instructions. LoCo seamlessly integrates into existing text-to-image and layout-to-image models, enhancing their performance in spatial control and addressing semantic failures observed in prior methods.
  arXiv  Detail & Related papers  (2023-11-21T04:28:12Z)
• Taming Encoder for Zero Fine-tuning Image Customization with Text-to-Image Diffusion Models [55.04969603431266]
  This paper proposes a method for generating images of customized objects specified by users. The method is based on a general framework that bypasses the lengthy optimization required by previous approaches. We demonstrate through experiments that our proposed method is able to synthesize images with compelling output quality, appearance diversity, and object fidelity.
  arXiv  Detail & Related papers  (2023-04-05T17:59:32Z)
• Structure-Guided Image Completion with Image-level and Object-level Semantic Discriminators [97.12135238534628]
  We propose a learning paradigm that consists of semantic discriminators and object-level discriminators for improving the generation of complex semantics and objects. Specifically, the semantic discriminators leverage pretrained visual features to improve the realism of the generated visual concepts. Our proposed scheme significantly improves the generation quality and achieves state-of-the-art results on various tasks.
  arXiv  Detail & Related papers  (2022-12-13T01:36:56Z)
• Instance Localization for Self-supervised Detection Pretraining [68.24102560821623]
  We propose a new self-supervised pretext task, called instance localization. We show that integration of bounding boxes into pretraining promotes better task alignment and architecture alignment for transfer learning. Experimental results demonstrate that our approach yields state-of-the-art transfer learning results for object detection.
  arXiv  Detail & Related papers  (2021-02-16T17:58:57Z)
• Object-Centric Image Generation from Layouts [93.10217725729468]
  We develop a layout-to-image-generation method to generate complex scenes with multiple objects. Our method learns representations of the spatial relationships between objects in the scene, which lead to our model's improved layout-fidelity. We introduce SceneFID, an object-centric adaptation of the popular Fr'echet Inception Distance metric, that is better suited for multi-object images.
  arXiv  Detail & Related papers  (2020-03-16T21:40:09Z)

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.