Hackers News

NeuralSVG: An Implicit Representation for Text-to-Vector Generation


Vector graphics are essential in design, providing artists with a versatile medium for creating resolution-independent
and highly editable visual content. Recent advancements in vision-language and diffusion models have fueled interest
in text-to-vector graphics generation. However, existing approaches often suffer from over-parameterized outputs or
treat the layered structure — a core feature of vector graphics — as a secondary goal, diminishing their practical
use. Recognizing the importance of layered SVG representations, we propose NeuralSVG, an implicit neural representation
for generating vector graphics from text prompts. Inspired by Neural Radiance Fields (NeRFs), NeuralSVG encodes the
entire scene into the weights of a small MLP network, optimized using Score Distillation Sampling (SDS). To encourage
a layered structure in the generated SVG, we introduce a dropout-based regularization technique that strengthens the
standalone meaning of each shape. We additionally demonstrate that utilizing a neural representation provides an added
benefit of inference-time control, enabling users to dynamically adapt the generated SVG based on user-provided inputs,
all with a single learned representation. Through extensive qualitative and quantitative evaluations, we demonstrate that
NeuralSVG outperforms existing methods in generating structured and flexible SVG.

admin

The realistic wildlife fine art paintings and prints of Jacquie Vaux begin with a deep appreciation of wildlife and the environment. Jacquie Vaux grew up in the Pacific Northwest, soon developed an appreciation for nature by observing the native wildlife of the area. Encouraged by her grandmother, she began painting the creatures she loves and has continued for the past four decades. Now a resident of Ft. Collins, CO she is an avid hiker, but always carries her camera, and is ready to capture a nature or wildlife image, to use as a reference for her fine art paintings.

Related Articles

Leave a Reply