RASP: Revisiting 3D Anamorphic Art for Shadow-Guided Packing of Irregular Objects

2025-04-03

AI Summary

This work addresses the problem of densely packing irregular 3D objects into a confined container while ensuring collision-free and boundary-respecting arrangements. We propose a shadow-guided differentiable optimization framework that optimizes multi-view silhouettes as the primary objective. Signed distance fields (SDFs) are employed to model inter-object penetration and container boundary violations, while a geometric consistency regularization enforces structural plausibility across views. Our key contributions are threefold: (i) the first end-to-end trainable 3D packing system integrating differentiable rendering with silhouette guidance; (ii) support for generating multi-view-consistent, artistically deformed object arrangements from a single input set; and (iii) extension to part-level assembly planning. Experiments demonstrate significant improvements in packing density and visual plausibility, validating practical utility in both artistic installation generation and industrial assembly planning.

Technology Category

• Computer Vision: 3D Computer Vision
• Constraint Satisfaction and Optimization: Mixed Discrete/Continuous Optimization
• Planning, Routing, and Scheduling: Optimization of Spatio-temporal Systems

Application Category

• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications
• Responsible Web: Human-perceived consequences of algorithmic deployment on the web
• Security and Privacy: Data transparency and provenance

Abstract

Recent advancements in learning-based methods have opened new avenues for exploring and interpreting art forms, such as shadow art, origami, and sketch art, through computational models. One notable visual art form is 3D Anamorphic Art in which an ensemble of arbitrarily shaped 3D objects creates a realistic and meaningful expression when observed from a particular viewpoint and loses its coherence over the other viewpoints. In this work, we build on insights from 3D Anamorphic Art to perform 3D object arrangement. We introduce RASP, a differentiable-rendering-based framework to arrange arbitrarily shaped 3D objects within a bounded volume via shadow (or silhouette)-guided optimization with an aim of minimal inter-object spacing and near-maximal occupancy. Furthermore, we propose a novel SDF-based formulation to handle inter-object intersection and container extrusion. We demonstrate that RASP can be extended to part assembly alongside object packing considering 3D objects to be"parts"of another 3D object. Finally, we present artistic illustrations of multi-view anamorphic art, achieving meaningful expressions from multiple viewpoints within a single ensemble.

Problem

• Optimize 3D object packing using shadow-guided anamorphic art principles
• Minimize inter-object spacing while maximizing occupancy in bounded volumes
• Enable multi-view anamorphic art with meaningful expressions from multiple angles

Innovation

• Differentiable-rendering-based framework for object arrangement
• SDF-based formulation for intersection handling
• Multi-view anamorphic art for meaningful expressions