Flow Plugin Network for conditional generation
Generative models have gained many researchers' attention in the last years resulting in models such as StyleGAN for human face generation or PointFlow for the 3D point cloud generation. However, by default, we cannot control its sampling process, i.e., we cannot generate a sample with a specific set of attributes. The current approach is model retraining with additional inputs and different architecture, which requires time and computational resources. We propose a novel approach that enables to a generation of objects with a given set of attributes without retraining the base model. For this purpose, we utilize the normalizing flow models - Conditional Masked Autoregressive Flow and Conditional Real NVP, as a Flow Plugin Network (FPN).
Code (1)
Tasks
Conditional Image GenerationFace GenerationImage GenerationImage ManipulationPoint Cloud GenerationMethods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
PluGeN: Multi-Label Conditional Generation From Pre-Trained Models
Modern generative models achieve excellent quality in a variety of tasks including image or text generation and chemical molecule modeling. However, existing methods often lack the essential ability to generate examples …
AttributeText GenerationWildFX: A DAW-Powered Pipeline for In-the-Wild Audio FX Graph Modeling
Despite rapid progress in end-to-end AI music generation, AI-driven modeling of professional Digital Signal Processing (DSP) workflows remains challenging. In particular, while there is growing interest in neural black-b…
Music GenerationOmniGen: Unified Image Generation
The emergence of Large Language Models (LLMs) has unified language generation tasks and revolutionized human-machine interaction. However, in the realm of image generation, a unified model capable of handling various tas…
Edge DetectionImage GenerationPose EstimationText Generation+3Towards democratizing music production with AI-Design of Variational Autoencoder-based Rhythm Generator as a DAW plugin
There has been significant progress in the music generation technique utilizing deep learning. However, it is still hard for musicians and artists to use these techniques in their daily music-making practice. This paper …
Deep LearningMusic GenerationRhythmCellProfiler plugins -- an easy image analysis platform integration for containers and Python tools
CellProfiler is a widely used software for creating reproducible, reusable image analysis workflows without needing to code. In addition to the >90 modules that make up the main CellProfiler program, CellProfiler has a p…