ShadowDraw: From Any Object to Shadow-Drawing Compositional Art

2025-12-04

AI Summary

This work addresses the problem of automatically generating shadow paintings for arbitrary 3D objects—artistic compositions where cast shadows and hand-drawn contours jointly form semantically recognizable imagery. The proposed method jointly optimizes object pose, lighting configuration, and sketch layout via differentiable rendering and gradient-based scene parameter optimization. It introduces a shadow-guided sketch generation network and a consistency-aware evaluation module to ensure visual fidelity and structural coherence. The framework supports multi-object scenes, dynamic animations, and physical deployment on real-world optical setups. Extensive experiments on real-world scanned models, synthetic assets, and complex compositional arrangements demonstrate high-quality, semantically coherent shadow paintings. Results validate the framework’s generality, robustness, and practical applicability, thereby advancing computational visual art by expanding both its design space and real-world deployability.

Technology Category

• Computer Vision: Computational Photography, Image & Video Synthesis
• Cognitive Modeling & Cognitive Systems: Computational Creativity
• Constraint Satisfaction and Optimization: Constraint Optimization

Application Category

• Economics, Online Markets and Human Computation: Economic ramifications for generative AI infrastructure and applications
• Responsible Web: Machine-in-the-loop, human agency and autonomy
• Graph Algorithms and Modeling for the Web: Efficient manipulation of static and dynamic Web-related graphs

Abstract

We introduce ShadowDraw, a framework that transforms ordinary 3D objects into shadow-drawing compositional art. Given a 3D object, our system predicts scene parameters, including object pose and lighting, together with a partial line drawing, such that the cast shadow completes the drawing into a recognizable image. To this end, we optimize scene configurations to reveal meaningful shadows, employ shadow strokes to guide line drawing generation, and adopt automatic evaluation to enforce shadow-drawing coherence and visual quality. Experiments show that ShadowDraw produces compelling results across diverse inputs, from real-world scans and curated datasets to generative assets, and naturally extends to multi-object scenes, animations, and physical deployments. Our work provides a practical pipeline for creating shadow-drawing art and broadens the design space of computational visual art, bridging the gap between algorithmic design and artistic storytelling. Check out our project page https://red-fairy.github.io/ShadowDraw/ for more results and an end-to-end real-world demonstration of our pipeline!

Problem

• Transforms 3D objects into shadow-drawing art
• Optimizes scene parameters to reveal meaningful shadows
• Generates line drawings completed by cast shadows

Innovation

• Optimizes scene parameters to create meaningful shadow compositions
• Uses shadow strokes to guide line drawing generation
• Automatically evaluates shadow-drawing coherence and visual quality