AttentionPainter: An Efficient and Adaptive Stroke Predictor for Scene Painting

• URL: http://arxiv.org/abs/2410.16418v2
• Date: Fri, 25 Oct 2024 11:39:43 GMT
• Title: AttentionPainter: An Efficient and Adaptive Stroke Predictor for Scene Painting
• Authors: Yizhe Tang, Yue Wang, Teng Hu, Ran Yi, Xin Tan, Lizhuang Ma, Yu-Kun Lai, Paul L. Rosin,
• Abstract summary: Stroke-based Rendering (SBR) aims to decompose an input image into a sequence of parameterized strokes, which can be rendered into a painting that resembles the input image. We propose AttentionPainter, an efficient and adaptive model for single-step neural painting.
• Score: 82.54770866332456
• License:
• Abstract: Stroke-based Rendering (SBR) aims to decompose an input image into a sequence of parameterized strokes, which can be rendered into a painting that resembles the input image. Recently, Neural Painting methods that utilize deep learning and reinforcement learning models to predict the stroke sequences have been developed, but suffer from longer inference time or unstable training. To address these issues, we propose AttentionPainter, an efficient and adaptive model for single-step neural painting. First, we propose a novel scalable stroke predictor, which predicts a large number of stroke parameters within a single forward process, instead of the iterative prediction of previous Reinforcement Learning or auto-regressive methods, which makes AttentionPainter faster than previous neural painting methods. To further increase the training efficiency, we propose a Fast Stroke Stacking algorithm, which brings 13 times acceleration for training. Moreover, we propose Stroke-density Loss, which encourages the model to use small strokes for detailed information, to help improve the reconstruction quality. Finally, we propose a new stroke diffusion model for both conditional and unconditional stroke-based generation, which denoises in the stroke parameter space and facilitates stroke-based inpainting and editing applications helpful for human artists design. Extensive experiments show that AttentionPainter outperforms the state-of-the-art neural painting methods.

Related papers

• PrefPaint: Aligning Image Inpainting Diffusion Model with Human Preference [62.72779589895124]
  We make the first attempt to align diffusion models for image inpainting with human aesthetic standards via a reinforcement learning framework. We train a reward model with a dataset we construct, consisting of nearly 51,000 images annotated with human preferences. Experiments on inpainting comparison and downstream tasks, such as image extension and 3D reconstruction, demonstrate the effectiveness of our approach.
  arXiv  Detail & Related papers  (2024-10-29T11:49:39Z)
• MambaPainter: Neural Stroke-Based Rendering in a Single Step [3.18005110016691]
  Stroke-based rendering aims to reconstruct an input image into an oil painting style by predicting brush stroke sequences. We propose MambaPainter, capable of predicting a sequence of over 100 brush strokes in a single inference step, resulting in rapid translation.
  arXiv  Detail & Related papers  (2024-10-16T13:02:45Z)
• ReNoise: Real Image Inversion Through Iterative Noising [62.96073631599749]
  We introduce an inversion method with a high quality-to-operation ratio, enhancing reconstruction accuracy without increasing the number of operations. We evaluate the performance of our ReNoise technique using various sampling algorithms and models, including recent accelerated diffusion models.
  arXiv  Detail & Related papers  (2024-03-21T17:52:08Z)
• Stroke-based Neural Painting and Stylization with Dynamically Predicted Painting Region [66.75826549444909]
  Stroke-based rendering aims to recreate an image with a set of strokes. We propose Compositional Neural Painter, which predicts the painting region based on the current canvas. We extend our method to stroke-based style transfer with a novel differentiable distance transform loss.
  arXiv  Detail & Related papers  (2023-09-07T06:27:39Z)
• Stroke-based Rendering: From Heuristics to Deep Learning [0.17188280334580194]
  Recent developments in deep learning methods help to bridge the gap between stroke-based paintings and pixel photo generation. We aim to provide a structured introduction and understanding of common challenges and approaches in stroke-based rendering algorithms.
  arXiv  Detail & Related papers  (2022-12-30T05:34:54Z)
• Learning Prior Feature and Attention Enhanced Image Inpainting [63.21231753407192]
  This paper incorporates the pre-training based Masked AutoEncoder (MAE) into the inpainting model. We propose to use attention priors from MAE to make the inpainting model learn more long-distance dependencies between masked and unmasked regions.
  arXiv  Detail & Related papers  (2022-08-03T04:32:53Z)
• Adaptive Perturbation for Adversarial Attack [50.77612889697216]
  We propose a new gradient-based attack method for adversarial examples. We use the exact gradient direction with a scaling factor for generating adversarial perturbations. Our method exhibits higher transferability and outperforms the state-of-the-art methods.
  arXiv  Detail & Related papers  (2021-11-27T07:57:41Z)
• Paint Transformer: Feed Forward Neural Painting with Stroke Prediction [36.457204758975074]
  We propose a novel Transformer-based framework, dubbed Paint Transformer, to predict the parameters of a stroke set with a feed forward network. This way, our model can generate a set of strokes in parallel and obtain the final painting of size 512 * 512 in near real time. Experiments demonstrate that our method achieves better painting performance than previous ones with cheaper training and inference costs.
  arXiv  Detail & Related papers  (2021-08-09T04:18:58Z)

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.