# COCO-GAN: Generation by Parts via Conditional Coordinating

arXiv: https://arxiv.org/abs/1904.00284 · HTML: https://mlsanity.com/paper/1904.00284/

## Key facts

- Cited by 67 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 30 Mar 2019.

## Built on by (most cited first, 30 of 67)

- [TransGAN: Two Pure Transformers Can Make One Strong GAN, and That Can Scale Up](https://mlsanity.com/paper/2102.07074/) (2021)
- [StyleSwin: Transformer-based GAN for High-resolution Image Generation](https://mlsanity.com/paper/2112.10762/) (2021)
- [Patch Diffusion: Faster and More Data-Efficient Training of Diffusion Models](https://mlsanity.com/paper/2304.12526/) (2023)
- [DiffuseVAE: Efficient, Controllable and High-Fidelity Generation from Low-Dimensional Latents](https://mlsanity.com/paper/2201.00308/) (2022)
- [DiffCollage: Parallel Generation of Large Content with Diffusion Models](https://mlsanity.com/paper/2303.17076/) (2023)
- [Accelerating Diffusion Models via Early Stop of the Diffusion Process](https://mlsanity.com/paper/2205.12524/) (2022)
- [Generative Models as Distributions of Functions](https://mlsanity.com/paper/2102.04776/) (2021)
- [PixNerd: Pixel Neural Field Diffusion](https://mlsanity.com/paper/2507.23268/) (2025)
- [Any-resolution Training for High-resolution Image Synthesis](https://mlsanity.com/paper/2204.07156/) (2022)
- [Aligning Latent and Image Spaces to Connect the Unconnectable](https://mlsanity.com/paper/2104.06954/) (2021)
- [InfiniCity: Infinite-Scale City Synthesis](https://mlsanity.com/paper/2301.09637/) (2023)
- [InfinityGAN: Towards Infinite-Pixel Image Synthesis](https://mlsanity.com/paper/2104.03963/) (2021)
- [Ctrl-Room: Controllable Text-to-3D Room Meshes Generation with Layout Constraints](https://mlsanity.com/paper/2310.03602/) (2023)
- [Improved Transformer for High-Resolution GANs](https://mlsanity.com/paper/2106.07631/) (2021)
- [Reverse Engineering of Generative Models: Inferring Model Hyperparameters from Generated Images](https://mlsanity.com/paper/2106.07873/) (2021)
- [360DVD: Controllable Panorama Video Generation with 360-Degree Video Diffusion Model](https://mlsanity.com/paper/2401.06578/) (2024)
- [Countering Malicious DeepFakes: Survey, Battleground, and Horizon](https://mlsanity.com/paper/2103.00218/) (2021)
- [In&Out : Diverse Image Outpainting via GAN Inversion](https://mlsanity.com/paper/2104.00675/) (2021)
- [Multimodal Image Synthesis and Editing: The Generative AI Era](https://mlsanity.com/paper/2112.13592/) (2021)
- [Diverse Plausible 360-Degree Image Outpainting for Efficient 3DCG Background Creation](https://mlsanity.com/paper/2203.14668/) (2022)
- [Customizing 360-Degree Panoramas through Text-to-Image Diffusion Models](https://mlsanity.com/paper/2310.18840/) (2023)
- [DU-GAN: Generative Adversarial Networks with Dual-Domain U-Net Based Discriminators for Low-Dose CT Denoising](https://mlsanity.com/paper/2108.10772/) (2021)
- [Patched Denoising Diffusion Models For High-Resolution Image Synthesis](https://mlsanity.com/paper/2308.01316/) (2023)
- [Truncated Diffusion Probabilistic Models and Diffusion-based Adversarial Auto-Encoders](https://mlsanity.com/paper/2202.09671/) (2022)
- [DivCo: Diverse Conditional Image Synthesis via Contrastive Generative Adversarial Network](https://mlsanity.com/paper/2103.07893/) (2021)
- [Guided Co-Modulated GAN for 360deg Field of View Extrapolation](https://mlsanity.com/paper/2204.07286/) (2022)
- [PS-NeRV: Patch-wise Stylized Neural Representations for Videos](https://mlsanity.com/paper/2208.03742/) (2022)
- [Dual Contrastive Loss and Attention for GANs](https://mlsanity.com/paper/2103.16748/) (2021)
- [Musika! Fast Infinite Waveform Music Generation](https://mlsanity.com/paper/2208.08706/) (2022)
- [Text2Light: Zero-Shot Text-Driven HDR Panorama Generation](https://mlsanity.com/paper/2209.09898/) (2022)

## Abstract (arXiv)

Humans can only interact with part of the surrounding environment due to biological restrictions. Therefore, we learn to reason the spatial relationships across a series of observations to piece together the surrounding environment. Inspired by such behavior and the fact that machines also have computational constraints, we propose underlineCOnditional underlineCOordinate GAN (COCO-GAN) of which the generator generates images by parts based on their spatial coordinates as the condition. On the other hand, the discriminator learns to justify realism across multiple assembled patches by global coherence, local appearance, and edge-crossing continuity. Despite the full images are never generated during training, we show that COCO-GAN can produce state-of-the-art-quality full images during inference. We further demonstrate a variety of novel applications enabled by teaching the network to be aware of coordinates. First, we perform extrapolation to the learned coordinate manifold and generate off-the-boundary patches. Combining with the originally generated full image, COCO-GAN can produce images that are larger than training samples, which we called "beyond-boundary generation". We then showcase panorama generation within a cylindrical coordinate system that inherently preserves horizontally cyclic topology. On the computation side, COCO-GAN has a built-in divide-and-conquer paradigm that reduces memory requisition during training and inference, provides high-parallelism, and can generate parts of images on-demand.