A generative model writes programs in a relational constraint DSL and uses bootstrapping to learn object placement distributions that align more closely with human annotations than data-driven or LLM baselines.
Fast and Flexible Indoor Scene Synthesis via Deep Convolutional Generative Models
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
abstract
We present a new, fast and flexible pipeline for indoor scene synthesis that is based on deep convolutional generative models. Our method operates on a top-down image-based representation, and inserts objects iteratively into the scene by predicting their category, location, orientation and size with separate neural network modules. Our pipeline naturally supports automatic completion of partial scenes, as well as synthesis of complete scenes. Our method is significantly faster than the previous image-based method and generates result that outperforms it and other state-of-the-art deep generative scene models in terms of faithfulness to training data and perceived visual quality.
verdicts
UNVERDICTED 2representative citing papers
SceneGraphNet uses attention-weighted neural message passing on scene graphs to predict fitting object types for augmenting incomplete 3D indoor scenes and reports outperformance versus prior methods on SUNCG.
citing papers explorer
-
SceneGraphNet: Neural Message Passing for 3D Indoor Scene Augmentation
SceneGraphNet uses attention-weighted neural message passing on scene graphs to predict fitting object types for augmenting incomplete 3D indoor scenes and reports outperformance versus prior methods on SUNCG.