MeronymNet: A Hierarchical Approach for Unified and Controllable Multi-Category Object Generation
Not on the map. Why?
Abstract (arXiv)
We introduce MeronymNet, a novel hierarchical approach for controllable, part-based generation of multi-category objects using a single unified model. We adopt a guided coarse-to-fine strategy involving semantically conditioned generation of bounding box layouts, pixel-level part layouts and ultimately, the object depictions themselves. We use Graph Convolutional Networks, Deep Recurrent Networks along with custom-designed Conditional Variational Autoencoders to enable flexible, diverse and category-aware generation of 2-D objects in a controlled manner. The performance scores for generated objects reflect MeronymNet's superior performance compared to multiple strong baselines and ablative variants. We also showcase MeronymNet's suitability for controllable object generation and interactive object editing at various levels of structural and semantic granularity.
Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 36 of its 49 references that are in the map. First posted on arXiv 17 Oct 2021.
Builds on
36 of 49 references.
References · 36
- 2014Adam: A Method for Stochastic Optimizationcited by 37,240
- 2016Semi-Supervised Classification with Graph Convolutional Networkscited by 11,361
- 2016Image-to-Image Translation with Conditional Adversarial Networkscited by 4,527
- 2013Auto-Encoding Variational Bayescited by 4,053
- 2018Large Scale GAN Training for High Fidelity Natural Image Synthesiscited by 2,626
- 2016Variational Graph Auto-Encoderscited by 1,382
- 2019Semantic Image Synthesis with Spatially-Adaptive Normalizationcited by 1,299
- 2016Conditional Image Synthesis With Auxiliary Classifier GANscited by 565
- 2018PartNet: A Large-scale Benchmark for Fine-grained and Hierarchical Part-level 3D Object Understandingcited by 526
- 2016Tutorial on Variational Autoencoderscited by 409
- 2018Graph R-CNN for Scene Graph Generationcited by 298
- 2018Auto-Encoding Scene Graphs for Image Captioningcited by 255
24 more
- 2017AttGAN: Facial Attribute Editing by Only Changing What You Wantcited by 242
- 2014Detect What You Can: Detecting and Representing Objects using Holistic Models and Body Partscited by 232
- 2017StackGAN++: Realistic Image Synthesis with Stacked Generative Adversarial Networkscited by 229
- 2018Pros and Cons of GAN Evaluation Measurescited by 224
- 2016UnitBox: An Advanced Object Detection Networkcited by 205
- 2019Semantic Graph Convolutional Networks for 3D Human Pose Regressioncited by 204
- 2019Cyclical Annealing Schedule: A Simple Approach to Mitigating KL Vanishingcited by 191
- 2018Constrained Graph Variational Autoencoders for Molecule Designcited by 185
- 2019LayoutGAN: Generating Graphic Layouts with Wireframe Discriminatorscited by 131
- 2019LayoutVAE: Stochastic Scene Layout Generation From a Label Setcited by 119
- 2019PQ-NET: A Generative Part Seq2Seq Network for 3D Shapescited by 119
- 2018Fast and Flexible Indoor Scene Synthesis via Deep Convolutional Generative Modelscited by 106
- 2018Image Generation from Layoutcited by 105
- 2019Scene Graph Generation with External Knowledge and Image Reconstructioncited by 102
- 2018Inferring Semantic Layout for Hierarchical Text-to-Image Synthesiscited by 101
- 2015Attribute2Image: Conditional Image Generation from Visual Attributescited by 93
- 2019Image Synthesis From Reconfigurable Layout and Stylecited by 85
- 2019Semantics Disentangling for Text-to-Image Generationcited by 61
- 2019Dual Graph Convolutional Network for Semantic Segmentationcited by 59
- 2020Baba is Y'all: Collaborative Mixed-Initiative Level Designcited by 20
- 2019Semantic Bottleneck Scene Generationcited by 19
- 2020Controllable Image Synthesis via SegVAEcited by 13
- 2018MC-GAN: Multi-conditional Generative Adversarial Network for Image Synthesiscited by 10
- 2018Graph Node-Feature Convolution for Representation Learningcited by 2
Built on by
Not cited yet.