mlsanityData to 7 Oct 2026

Pluralistic Image Completion with Probabilistic Mixture-of-Experts

arXiv 2205.09086 ↗First posted 18 May 2022cs.CV cs.LGcited by 1

On the map: Mixture-of-experts → Vision mixture-of-experts

Abstract (arXiv)

Pluralistic image completion focuses on generating both visually realistic and diverse results for image completion. Prior methods enjoy the empirical successes of this task. However, their used constraints for pluralistic image completion are argued to be not well interpretable and unsatisfactory from two aspects. First, the constraints for visual reality can be weakly correlated to the objective of image completion or even redundant. Second, the constraints for diversity are designed to be task-agnostic, which causes the constraints to not work well. In this paper, to address the issues, we propose an end-to-end probabilistic method. Specifically, we introduce a unified probabilistic graph model that represents the complex interactions in image completion. The entire procedure of image completion is then mathematically divided into several sub-procedures, which helps efficient enforcement of constraints. The sub-procedure directly related to pluralistic results is identified, where the interaction is established by a Gaussian mixture model (GMM). The inherent parameters of GMM are task-related, which are optimized adaptively during training, while the number of its primitives can control the diversity of results conveniently. We formally establish the effectiveness of our method and demonstrate it with comprehensive experiments.

Key facts. Cited by 1 paper in the map (data through 7 Oct 2026). Placed in Vision mixture-of-experts, one of 12 directions in Mixture-of-experts. Builds on 28 of its 55 references that are in the map. First posted on arXiv 18 May 2022.

Builds on

28 of 55 references.

References · 28

  1. 2014Adam: A Method for Stochastic Optimizationcited by 36,960
  2. 2014ImageNet Large Scale Visual Recognition Challengecited by 8,441
  3. 2018A Style-Based Generator Architecture for Generative Adversarial Networkscited by 5,986
  4. 2022Generative Adversarial Networkscited by 5,603
  5. 2013Auto-Encoding Variational Bayescited by 3,980
  6. 2014Deep Learning Face Attributes in the Wildcited by 3,679
  7. 2017Progressive Growing of GANs for Improved Quality, Stability, and Variationcited by 2,967
  8. 2016Context Encoders: Feature Learning by Inpaintingcited by 1,424
  9. 2016Least Squares Generative Adversarial Networkscited by 1,000
  10. 2018Image Transformercited by 770
  11. 2018Free-Form Image Inpainting with Gated Convolutioncited by 594
  12. 2018Generative Image Inpainting with Contextual Attentioncited by 578
16 more
  1. 2019Pluralistic Image Completioncited by 162
  2. 2019EdgeConnect: Generative Image Inpainting with Adversarial Edge Learningcited by 161
  3. 2021High-Fidelity Pluralistic Image Completion with Transformerscited by 134
  4. 2020Contextual Residual Aggregation for Ultra High-Resolution Image Inpaintingcited by 124
  5. 2021Generating Diverse Structure for Image Inpainting With Hierarchical VQ-VAEcited by 106
  6. 2020Rethinking Image Inpainting via a Mutual Encoder-Decoder with Feature Equalizationscited by 102
  7. 2019Learning Pyramid-Context Encoder Network for High-Quality Image Inpaintingcited by 94
  8. 2018Shift-Net: Image Inpainting via Deep Feature Rearrangementcited by 87
  9. 2016An Uncertain Future: Forecasting from Static Images using Variational Autoencoderscited by 86
  10. 2021PD-GAN: Probabilistic Diverse GAN for Image Inpaintingcited by 80
  11. 2017Generative Face Completioncited by 79
  12. 2017UV-GAN: Adversarial Facial UV Map Completion for Pose-invariant Face Recognitioncited by 62
  13. 2019Compatible and Diverse Fashion Image Inpaintingcited by 26
  14. 2021Probabilistic Mixture-of-Experts for Efficient Deep Reinforcement Learningcited by 26
  15. 2017Eye In-Painting with Exemplar Generative Adversarial Networkscited by 18
  16. 2020Adaptive Semantic-Visual Tree for Hierarchical Embeddingscited by 8

Built on by

Cited by year

Citing papers per year: 2024: 1.

1 paper.

  1. 2024Integration of Mixture of Experts and Multimodal Generative AI in Internet of Vehicles: A Surveycited by 6

Similar, not cited

Close in wording, no citation either way

  1. 2022A Structure-Guided Diffusion Model for Large-Hole Image Completion
  2. 2025Evaluating Latent Generative Paradigms for High-Fidelity 3D Shape Completion from a Single Depth Image
  3. 2023One at a Time: Progressive Multi-step Volumetric Probability Learning for Reliable 3D Scene Perception
  4. 2025From Missing Pieces to Masterpieces: Image Completion with Context-Adaptive Diffusion
  5. 2023DiffComplete: Diffusion-based Generative 3D Shape Completion
  6. 2026Integrating Multimodal Large Language Model Knowledge into Amodal Completion
  7. 2024Consistency-diversity-realism Pareto fronts of conditional image generative models
  8. 2021Generative Probabilistic Image Colorization