GrounDiT: Grounding Diffusion Transformers via Noisy Patch Transplantation

• URL: http://arxiv.org/abs/2410.20474v2
• Date: Fri, 01 Nov 2024 04:33:52 GMT
• Title: GrounDiT: Grounding Diffusion Transformers via Noisy Patch Transplantation
• Authors: Phillip Y. Lee, Taehoon Yoon, Minhyuk Sung,
• Abstract summary: We introduce GrounDiT, a training-free spatial grounding technique for text-to-image generation using Diffusion Transformers (DiT) We leverage the flexibility of the Transformer architecture, demonstrating that DiT can generate noisy patches corresponding to each bounding box. Our approach builds on an intriguing property of DiT, which we refer to as semantic sharing.
• Score: 11.517082612850443
• License:
• Abstract: We introduce GrounDiT, a novel training-free spatial grounding technique for text-to-image generation using Diffusion Transformers (DiT). Spatial grounding with bounding boxes has gained attention for its simplicity and versatility, allowing for enhanced user control in image generation. However, prior training-free approaches often rely on updating the noisy image during the reverse diffusion process via backpropagation from custom loss functions, which frequently struggle to provide precise control over individual bounding boxes. In this work, we leverage the flexibility of the Transformer architecture, demonstrating that DiT can generate noisy patches corresponding to each bounding box, fully encoding the target object and allowing for fine-grained control over each region. Our approach builds on an intriguing property of DiT, which we refer to as semantic sharing. Due to semantic sharing, when a smaller patch is jointly denoised alongside a generatable-size image, the two become semantic clones. Each patch is denoised in its own branch of the generation process and then transplanted into the corresponding region of the original noisy image at each timestep, resulting in robust spatial grounding for each bounding box. In our experiments on the HRS and DrawBench benchmarks, we achieve state-of-the-art performance compared to previous training-free approaches.

Related papers

• CT-Bound: Robust Boundary Detection From Noisy Images Via Hybrid Convolution and Transformer Neural Networks [10.622511683372815]
  We present CT-Bound, a robust and fast boundary detection method for very noisy images using a hybrid Convolution and Transformer neural network. During the local detection, the model uses a convolutional architecture to predict the boundary structure of each image patch. Then, it uses a feed-forward transformer architecture to globally refine the boundary structures of each patch to generate an edge map and a smoothed color map simultaneously.
  arXiv  Detail & Related papers  (2024-03-25T07:22:22Z)
• Hyper-VolTran: Fast and Generalizable One-Shot Image to 3D Object Structure via HyperNetworks [53.67497327319569]
  We introduce a novel neural rendering technique to solve image-to-3D from a single view. Our approach employs the signed distance function as the surface representation and incorporates generalizable priors through geometry-encoding volumes and HyperNetworks. Our experiments show the advantages of our proposed approach with consistent results and rapid generation.
  arXiv  Detail & Related papers  (2023-12-24T08:42:37Z)
• Unified Frequency-Assisted Transformer Framework for Detecting and Grounding Multi-Modal Manipulation [109.1912721224697]
  We present the Unified Frequency-Assisted transFormer framework, named UFAFormer, to address the DGM4 problem. By leveraging the discrete wavelet transform, we decompose images into several frequency sub-bands, capturing rich face forgery artifacts. Our proposed frequency encoder, incorporating intra-band and inter-band self-attentions, explicitly aggregates forgery features within and across diverse sub-bands.
  arXiv  Detail & Related papers  (2023-09-18T11:06:42Z)
• Accurate Image Restoration with Attention Retractable Transformer [50.05204240159985]
  We propose Attention Retractable Transformer (ART) for image restoration. ART presents both dense and sparse attention modules in the network. We conduct extensive experiments on image super-resolution, denoising, and JPEG compression artifact reduction tasks.
  arXiv  Detail & Related papers  (2022-10-04T07:35:01Z)
• ResT: An Efficient Transformer for Visual Recognition [5.807423409327807]
  This paper presents an efficient multi-scale vision Transformer, called ResT, that capably served as a general-purpose backbone for image recognition. We show that the proposed ResT can outperform the recently state-of-the-art backbones by a large margin, demonstrating the potential of ResT as strong backbones.
  arXiv  Detail & Related papers  (2021-05-28T08:53:54Z)
• TWIST-GAN: Towards Wavelet Transform and Transferred GAN for Spatio-Temporal Single Image Super Resolution [4.622977798361014]
  Single Image Super-resolution (SISR) produces high-resolution images with fine spatial resolutions from a remotely sensed image with low spatial resolution. Deep learning and generative adversarial networks (GANs) have made breakthroughs for the challenging task of single image super-resolution (SISR)
  arXiv  Detail & Related papers  (2021-04-20T22:12:38Z)
• TFill: Image Completion via a Transformer-Based Architecture [69.62228639870114]
  We propose treating image completion as a directionless sequence-to-sequence prediction task. We employ a restrictive CNN with small and non-overlapping RF for token representation. In a second phase, to improve appearance consistency between visible and generated regions, a novel attention-aware layer (AAL) is introduced.
  arXiv  Detail & Related papers  (2021-04-02T01:42:01Z)
• Image-to-image Mapping with Many Domains by Sparse Attribute Transfer [71.28847881318013]
  Unsupervised image-to-image translation consists of learning a pair of mappings between two domains without known pairwise correspondences between points. Current convention is to approach this task with cycle-consistent GANs. We propose an alternate approach that directly restricts the generator to performing a simple sparse transformation in a latent layer.
  arXiv  Detail & Related papers  (2020-06-23T19:52:23Z)
• Image Fine-grained Inpainting [89.17316318927621]
  We present a one-stage model that utilizes dense combinations of dilated convolutions to obtain larger and more effective receptive fields. To better train this efficient generator, except for frequently-used VGG feature matching loss, we design a novel self-guided regression loss. We also employ a discriminator with local and global branches to ensure local-global contents consistency.
  arXiv  Detail & Related papers  (2020-02-07T03:45:25Z)

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.