CLIPDraw++: Text-to-Sketch Synthesis with Simple Primitives
Not on the map. Why?
Abstract (arXiv)
With the goal of understanding the visual concepts that CLIP associates with text prompts, we show that the latent space of CLIP can be visualized solely in terms of linear transformations on simple geometric primitives like straight lines and circles. Although existing approaches achieve this by sketch-synthesis-through-optimization, they do so on the space of higher order B'ezier curves, which exhibit a wastefully large set of structures that they can evolve into, as most of them are non-essential for generating meaningful sketches. We present CLIPDraw++, an algorithm that provides significantly better visualizations for CLIP text embeddings, using only simple primitive shapes like straight lines and circles. This constrains the set of possible outputs to linear transformations on these primitives, thereby exhibiting an inherently simpler mathematical form. The synthesis process of CLIPDraw++ can be tracked end-to-end, with each visual concept being expressed exclusively in terms of primitives. Project Page: https://clipdrawx.github.io/.
Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 24 of its 34 references that are in the map. First posted on arXiv 4 Dec 2023.
Builds on
24 of 34 references.
References · 24
- 2021Learning Transferable Visual Models From Natural Language Supervisioncited by 33,456
- 2019PyTorch: An Imperative Style, High-Performance Deep Learning Librarycited by 20,160
- 2021High-Resolution Image Synthesis with Latent Diffusion Modelscited by 18,694
- 2022BLIP: Bootstrapping Language-Image Pre-training for Unified Vision-Language Understanding and Generationcited by 4,310
- 2014Deep Neural Networks are Easily Fooled: High Confidence Predictions for Unrecognizable Imagescited by 774
- 2017A Neural Representation of Sketch Drawingscited by 311
- 2022What the DAAM: Interpreting Stable Diffusion Using Cross Attentioncited by 233
- 2021CLIPDraw: Exploring Text-to-Drawing Synthesis through Language-Image Encoderscited by 186
- 2016Synthesizing the preferred inputs for neurons in neural networks via deep generator networkscited by 181
- 2022VectorFusion: Text-to-SVG by Abstracting Pixel-Based Diffusion Modelscited by 112
- 2022Learning to generate line drawings that convey geometry and semanticscited by 82
- 2019Photo-Sketching: Inferring Contour Drawings from Imagescited by 67
12 more
- 2022CLIPascene: Scene Sketching with Different Types and Levels of Abstractioncited by 63
- 2021Generating images from caption and vice versa via CLIP-Guided Generative Latent Space Searchcited by 57
- 2022CLIPasso: Semantically-Aware Object Sketchingcited by 57
- 2023DiffSketcher: Text Guided Vector Sketch Synthesis through Latent Diffusion Modelscited by 54
- 2019Unsupervised Sketch-to-Photo Synthesiscited by 38
- 2020Deep Generation of Face Images from Sketchescited by 32
- 2021DoodleFormer: Creative Sketch Drawing with Transformerscited by 17
- 2015Free-hand Sketch Synthesis with Deformable Stroke Modelscited by 16
- 2022Abstracting Sketches through Simple Primitivescited by 14
- 2022CLIP-CLOP: CLIP-Guided Collage and Photomontagecited by 11
- 2023SketchXAI: A First Look at Explainability for Human Sketchescited by 10
- 2020Sketch Generation with Drawing Process Guided by Vector Flow and Grayscalecited by 8
Built on by
Not cited yet.