Procedural Scene Programs for Open-Universe Scene Generation: LLM-Free Error Correction via Program Search
October 17, 2025 Β· Declared Dead Β· π ACM SIGGRAPH Conference and Exhibition on Computer Graphics and Interactive Techniques in Asia
"No code URL or promise found in abstract"
Evidence collected by the PWNC Scanner
Authors
Maxim Gumin, Do Heon Han, Seung Jean Yoo, Aditya Ganeshan, R. Kenny Jones, Kailiang Fu, Rio Aguina-Kang, Stewart Morris, Daniel Ritchie
arXiv ID
2510.16147
Category
cs.GR: Graphics
Citations
1
Venue
ACM SIGGRAPH Conference and Exhibition on Computer Graphics and Interactive Techniques in Asia
Last Checked
5 months ago
Abstract
Synthesizing 3D scenes from open-vocabulary text descriptions is a challenging, important, and recently-popular application. One of its critical subproblems is layout generation: given a set of objects, lay them out to produce a scene matching the input description. Nearly all recent work adopts a declarative paradigm for this problem: using an LLM to generate a specification of constraints between objects, then solving those constraints to produce the final layout. In contrast, we explore an alternative imperative paradigm, in which an LLM iteratively places objects, with each object's position and orientation computed as a function of previously-placed objects. The imperative approach allows for a simpler scene specification language while also handling a wider variety and larger complexity of scenes. We further improve the robustness of our imperative scheme by developing an error correction mechanism that iteratively improves the scene's validity while staying as close as possible to the original layout generated by the LLM. In forced-choice perceptual studies, participants preferred layouts generated by our imperative approach 82% and 94% of the time when compared against two declarative layout generation methods. We also present a simple, automated evaluation metric for 3D scene layout generation that aligns well with human preferences.
Community Contributions
Found the code? Know the venue? Think something is wrong? Let us know!
π Similar Papers
In the same crypt β Graphics
R.I.P.
π»
Ghosted
R.I.P.
π»
Ghosted
Deep Bilateral Learning for Real-Time Image Enhancement
R.I.P.
π»
Ghosted
Animating Human Athletics
R.I.P.
π»
Ghosted
BundleFusion: Real-time Globally Consistent 3D Reconstruction using On-the-fly Surface Re-integration
R.I.P.
π»
Ghosted
Shape Transformation Using Variational Implicit Functions
R.I.P.
π»
Ghosted
ABC: A Big CAD Model Dataset For Geometric Deep Learning
Died the same way β π» Ghosted
R.I.P.
π»
Ghosted
Federated Learning: Strategies for Improving Communication Efficiency
R.I.P.
π»
Ghosted
In-Datacenter Performance Analysis of a Tensor Processing Unit
R.I.P.
π»
Ghosted
Deep Convolutional Neural Networks for Computer-Aided Detection: CNN Architectures, Dataset Characteristics and Transfer Learning
R.I.P.
π»
Ghosted