Layered Image Vectorization via Semantic Simplification
- URL: http://arxiv.org/abs/2406.05404v1
- Date: Sat, 8 Jun 2024 08:54:35 GMT
- Title: Layered Image Vectorization via Semantic Simplification
- Authors: Zhenyu Wang, Jianxi Huang, Zhida Sun, Daniel Cohen-Or, Min Lu,
- Abstract summary: This work presents a novel progressive image vectorization technique aimed at generating layered vectors that represent the original image from coarse to fine detail levels.
Our approach introduces semantic simplification, which combines Score Distillation Sampling and semantic segmentation to iteratively simplify the input image.
Our method provides robust optimization, which avoids local minima and enables adjustable detail levels in the final output.
- Score: 46.23779847614095
- License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
- Abstract: This work presents a novel progressive image vectorization technique aimed at generating layered vectors that represent the original image from coarse to fine detail levels. Our approach introduces semantic simplification, which combines Score Distillation Sampling and semantic segmentation to iteratively simplify the input image. Subsequently, our method optimizes the vector layers for each of the progressively simplified images. Our method provides robust optimization, which avoids local minima and enables adjustable detail levels in the final output. The layered, compact vector representation enhances usability for further editing and modification. Comparative analysis with conventional vectorization methods demonstrates our technique's superiority in producing vectors with high visual fidelity, and more importantly, maintaining vector compactness and manageability. The project homepage is https://szuviz.github.io/layered_vectorization/.
Related papers
- SwiftSketch: A Diffusion Model for Image-to-Vector Sketch Generation [57.47730473674261]
We introduce SwiftSketch, a model for image-conditioned vector sketch generation that can produce high-quality sketches in less than a second.
SwiftSketch operates by progressively denoising stroke control points sampled from a Gaussian distribution.
ControlSketch is a method that enhances SDS-based techniques by incorporating precise spatial control through a depth-aware ControlNet.
arXiv Detail & Related papers (2025-02-12T18:57:12Z) - SVGDreamer++: Advancing Editability and Diversity in Text-Guided SVG Generation [31.76771064173087]
We propose a novel text-guided vector graphics synthesis method to address limitations of existing methods.
We introduce a Hierarchical Image VEctorization (HIVE) framework that operates at the semantic object level.
We also present a Vectorized Particle-based Score Distillation (VPSD) approach to improve the diversity of output SVGs.
arXiv Detail & Related papers (2024-11-26T19:13:38Z) - Segmentation-guided Layer-wise Image Vectorization with Gradient Fills [6.037332707968933]
We propose a segmentation-guided vectorization framework to convert images into concise vector graphics with gradient fills.
With the guidance of an embedded gradient-aware segmentation, our approach progressively appends gradient-filled B'ezier paths to the output.
arXiv Detail & Related papers (2024-08-28T12:08:25Z) - SuperSVG: Superpixel-based Scalable Vector Graphics Synthesis [66.44553285020066]
SuperSVG is a superpixel-based vectorization model that achieves fast and high-precision image vectorization.
We propose a two-stage self-training framework, where a coarse-stage model is employed to reconstruct the main structure and a refinement-stage model is used for enriching the details.
Experiments demonstrate the superior performance of our method in terms of reconstruction accuracy and inference time compared to state-of-the-art approaches.
arXiv Detail & Related papers (2024-06-14T07:43:23Z) - VectorPainter: Advanced Stylized Vector Graphics Synthesis Using Stroke-Style Priors [18.477188153621125]
We introduce VectorPainter, a novel framework designed for reference-guided text-to-vector-graphics synthesis.
Our method first converts the pixels of the reference image into a series of vector strokes, and then generates a vector graphic based on the input text description.
To preserve the style of the strokes throughout the generation process, we introduce a style-preserving loss function.
arXiv Detail & Related papers (2024-05-05T15:01:29Z) - Texture, Shape and Order Matter: A New Transformer Design for Sequential DeepFake Detection [57.100891917805086]
Sequential DeepFake detection is an emerging task that predicts the manipulation sequence in order.
This paper describes a new Transformer design, called TSOM, by exploring three perspectives: Texture, Shape, and Order of Manipulations.
arXiv Detail & Related papers (2024-04-22T04:47:52Z) - StrokeNUWA: Tokenizing Strokes for Vector Graphic Synthesis [112.25071764647683]
StrokeNUWA is a pioneering work exploring a better visual representation ''stroke tokens'' on vector graphics.
equipped with stroke tokens, StrokeNUWA can significantly surpass traditional LLM-based and optimization-based methods.
StrokeNUWA achieves up to a 94x speedup in inference over the speed of prior methods with an exceptional SVG code compression ratio of 6.9%.
arXiv Detail & Related papers (2024-01-30T15:20:26Z) - Optimize and Reduce: A Top-Down Approach for Image Vectorization [12.998637003026273]
We propose Optimize & Reduce (O&R), a top-down approach to vectorization that is both fast and domain-agnostic.
O&R aims to attain a compact representation of input images by iteratively optimizing B'ezier curve parameters.
We demonstrate that our method is domain agnostic and outperforms existing works in both reconstruction and perceptual quality for a fixed number of shapes.
arXiv Detail & Related papers (2023-12-18T16:41:03Z) - Improving Image Tracing with Convolutional Autoencoders by High-Pass
Filter Preprocessing [0.6367279911825442]
This study looks into several processing methods that include high-pass filtering, autoencoding, and vectorization to extract an abstract representation of an image.
According to the findings, rebuilding an image with autoencoders, high-pass filtering it, and then vectorizing it can represent the image more abstractly while increasing the effectiveness of the vectorization process.
arXiv Detail & Related papers (2023-06-15T10:59:29Z) - Towards Layer-wise Image Vectorization [57.26058135389497]
We propose Layerwise Image Vectorization, namely LIVE, to convert images to SVGs and simultaneously maintain its image topology.
Live generates compact forms with layer-wise structures that are semantically consistent with human perspective.
Live initiates human editable SVGs for both designers and can be used in other applications.
arXiv Detail & Related papers (2022-06-09T17:55:02Z)
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.