# Multimodal Image Synthesis with Conditional Implicit Maximum Likelihood Estimation

arXiv: https://arxiv.org/abs/2004.03590 · HTML: https://mlsanity.com/paper/2004.03590/

## Key facts

- Cited by 13 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 7 Apr 2020.

## Built on by (most cited first, 13 of 13)

- [Towards Implicit Text-Guided 3D Shape Generation](https://mlsanity.com/paper/2203.14622/) (2022)
- [SCADE: NeRFs from Space Carving with Ambiguity-Aware Depth Estimates](https://mlsanity.com/paper/2303.13582/) (2023)
- [DiffFacto: Controllable Part-Based 3D Point Cloud Generation with Cross Diffusion](https://mlsanity.com/paper/2305.01921/) (2023)
- [Conditional Image Generation by Conditioning Variational Auto-Encoders](https://mlsanity.com/paper/2102.12037/) (2021)
- [Closed-Loop Data Transcription to an LDR via Minimaxing Rate Reduction](https://mlsanity.com/paper/2111.06636/) (2021)
- [PAPR: Proximity Attention Point Rendering](https://mlsanity.com/paper/2307.11086/) (2023)
- [Multimodal Shape Completion via IMLE](https://mlsanity.com/paper/2106.16237/) (2021)
- [CHIMLE: Conditional Hierarchical IMLE for Multimodal Conditional Image Synthesis](https://mlsanity.com/paper/2211.14286/) (2022)
- [Implicit Maximum Likelihood Estimation for Real-time Generative Model Predictive Control](https://mlsanity.com/paper/2603.13733/) (2026)
- [How Good Are Deep Generative Models for Solving Inverse Problems?](https://mlsanity.com/paper/2312.12691/) (2023)
- [Cascading Modular Network (CAM-Net) for Multimodal Image Synthesis](https://mlsanity.com/paper/2106.09015/) (2021)
- [On Interpretable Approaches to Cluster, Classify and Represent Multi-Subspace Data via Minimum Lossy Coding Length based on Rate-Distortion Theory](https://mlsanity.com/paper/2302.10383/) (2023)
- [Diverse Part Synthesis for 3D Shape Creation](https://mlsanity.com/paper/2401.09384/) (2024)

## Abstract (arXiv)

Many tasks in computer vision and graphics fall within the framework of conditional image synthesis. In recent years, generative adversarial nets (GANs) have delivered impressive advances in quality of synthesized images. However, it remains a challenge to generate both diverse and plausible images for the same input, due to the problem of mode collapse. In this paper, we develop a new generic multimodal conditional image synthesis method based on Implicit Maximum Likelihood Estimation (IMLE) and demonstrate improved multimodal image synthesis performance on two tasks, single image super-resolution and image synthesis from scene layouts. We make our implementation publicly available.