Clair Obscur: an Illumination-Aware Method for Real-World Image Vectorization

• URL: http://arxiv.org/abs/2511.20034v1
• Date: Tue, 25 Nov 2025 08:01:04 GMT
• Title: Clair Obscur: an Illumination-Aware Method for Real-World Image Vectorization
• Authors: Xingyue Lin, Shuai Peng, Xiangyu Xie, Jianhua Zhu, Yuxuan Zhou, Liangcai Gao,
• Abstract summary: COVec is an illumination-aware vectorization framework inspired by the Clair-Obscur principle of light-shade contrast.<n>It is the first to introduce intrinsic image decomposition in the vector domain, separating an image into albedo, shade, and light layers in a unified vector representation.
• Score: 12.638057671088148
• License: http://creativecommons.org/licenses/by-sa/4.0/
• Abstract: Image vectorization aims to convert raster images into editable, scalable vector representations while preserving visual fidelity. Existing vectorization methods struggle to represent complex real-world images, often producing fragmented shapes at the cost of semantic conciseness. In this paper, we propose COVec, an illumination-aware vectorization framework inspired by the Clair-Obscur principle of light-shade contrast. COVec is the first to introduce intrinsic image decomposition in the vector domain, separating an image into albedo, shade, and light layers in a unified vector representation. A semantic-guided initialization and two-stage optimization refine these layers with differentiable rendering. Experiments on various datasets demonstrate that COVec achieves higher visual fidelity and significantly improved editability compared to existing methods.

Related papers

• Controlling Your Image via Simplified Vector Graphics [31.087153372906624]
  We introduce layer-wise controllable generation through simplified vector graphics (VGs)<n>Our approach first efficiently parses images into hierarchical VG representations that are semantic-aligned and structurally coherent.<n>Building on this representation, we design a novel image synthesis framework guided by VGs, allowing users to freely modify elements and seamlessly translate these edits into outputs.
  arXiv  Detail & Related papers  (2026-02-16T03:56:42Z)
• Illustrator's Depth: Monocular Layer Index Prediction for Image Decomposition [55.8308608221966]
  We introduce Illustrator's Depth, a novel definition of depth that addresses a key challenge in digital content creation: decomposing flat images into editable, ordered layers.<n>Inspired by an artist's compositional process, illustrator's depth infers a layer index to each pixel, forming an interpretable image decomposition.
  arXiv  Detail & Related papers  (2025-11-21T17:56:43Z)
• Materialist: Physically Based Editing Using Single-Image Inverse Rendering [47.85234717907478]
  Materialist is a method combining a learning-based approach with physically based progressive differentiable rendering.<n>Our approach enables a range of applications, including material editing, object insertion, and relighting.<n> Experiments demonstrate strong performance across synthetic and real-world datasets.
  arXiv  Detail & Related papers  (2025-01-07T11:52:01Z)
• DeepIcon: A Hierarchical Network for Layer-wise Icon Vectorization [12.82009632507056]
  Recent learning-based methods for converting images to vector formats frequently suffer from incomplete shapes, redundant path prediction, and a lack of accuracy in preserving the semantics of the original content. We present DeepIcon, a novel hierarchical image vectorization network specifically tailored generating variable-length icon graphics based on the image input.
  arXiv  Detail & Related papers  (2024-10-21T08:20:19Z)
• 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)
• Layered Image Vectorization via Semantic Simplification [45.55066618943338]
  This work presents a progressive image vectorization technique that reconstructs the image as layer-wise vectors from semantic-aligned macro structures to finer details.<n>Our approach introduces a new image simplification method leveraging the feature-average effect in the Score Distillation Sampling mechanism.<n>The resulting vectors are layered and well-aligned with the target image's explicit and implicit semantic structures.
  arXiv  Detail & Related papers  (2024-06-08T08:54:35Z)
• 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)
• NeFII: Inverse Rendering for Reflectance Decomposition with Near-Field Indirect Illumination [48.42173911185454]
  Inverse rendering methods aim to estimate geometry, materials and illumination from multi-view RGB images. We propose an end-to-end inverse rendering pipeline that decomposes materials and illumination from multi-view images.
  arXiv  Detail & Related papers  (2023-03-29T12:05:19Z)
• DIB-R++: Learning to Predict Lighting and Material with a Hybrid Differentiable Renderer [78.91753256634453]
  We consider the challenging problem of predicting intrinsic object properties from a single image by exploiting differentiables. In this work, we propose DIBR++, a hybrid differentiable which supports these effects by combining specularization and ray-tracing. Compared to more advanced physics-based differentiables, DIBR++ is highly performant due to its compact and expressive model.
  arXiv  Detail & Related papers  (2021-10-30T01:59:39Z)
• Deep CG2Real: Synthetic-to-Real Translation via Image Disentanglement [78.58603635621591]
  Training an unpaired synthetic-to-real translation network in image space is severely under-constrained. We propose a semi-supervised approach that operates on the disentangled shading and albedo layers of the image. Our two-stage pipeline first learns to predict accurate shading in a supervised fashion using physically-based renderings as targets.
  arXiv  Detail & Related papers  (2020-03-27T21:45:41Z)

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.