SandSim: Curve-Guided Gaussian Splatting for Reconstructing Sand Painting Processes

2026-04-30

AI Summary

This work addresses the challenge of reconstructing a structurally coherent and materially consistent sand animation process from a single image by proposing a curve-guided Gaussian representation. The method models sand strokes as sequences of anisotropic primitives aligned along continuous trajectories and incorporates subtractive compositing to simulate light attenuation caused by sand pile-up. A semantic-guided stroke ordering mechanism is introduced to infer plausible drawing sequences. By jointly optimizing stroke geometry and appearance, and integrating physics-based simulation to support interactive editing, the approach significantly outperforms existing techniques in both reconstruction fidelity and temporal coherence, producing visually realistic animations that adhere to the physical characteristics of sand art.

Abstract

Sand painting is a process-driven art where visual appearance emerges from granular accumulation. Given a single image, reconstructing a plausible sand painting process requires modeling coherent stroke structures and material-dependent effects. Existing methods, including stroke-based optimization and diffusion-based video synthesis, often lack structural coherence and material consistency, leading to unrealistic drawing sequences. We present SandSim, a framework that reconstructs a sand painting process from a single image. We introduce a curve-guided Gaussian representation that models strokes as sequences of anisotropic primitives along continuous trajectories, whose smooth kernels capture the soft boundaries of sand strokes and enable coherent stroke formation. We further adopt a subtractive compositing scheme to model light attenuation during sand accumulation. We incorporate a semantic-guided planning module for scene decomposition and drawing order inference. Our framework jointly optimizes stroke geometry and appearance and can be integrated with a physics-based simulator for interactive sand dynamics and editing. Experiments show that our method produces temporally coherent and visually realistic results, achieving improved reconstruction quality and perceptual fidelity compared to existing approaches.

Problem

• sand painting
• process reconstruction
• structural coherence
• material consistency
• stroke modeling

Innovation

• curve-guided Gaussian splatting
• sand painting reconstruction
• subtractive compositing
• stroke coherence
• semantic-guided planning