# GRAM-HD: 3D-Consistent Image Generation at High Resolution with Generative Radiance Manifolds

arXiv: https://arxiv.org/abs/2206.07255 · HTML: https://mlsanity.com/paper/2206.07255/

## Key facts

- Cited by 73 papers in the map (data through 14 Oct 2026).
- Builds on 58 of its 79 references that are in the map.
- First posted on arXiv 15 Jun 2022.

## Builds on (most cited first, 30 of 58)

- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [The Unreasonable Effectiveness of Deep Features as a Perceptual Metric](https://mlsanity.com/paper/1801.03924/) (2018)
- [A Style-Based Generator Architecture for Generative Adversarial Networks](https://mlsanity.com/paper/1812.04948/) (2018)
- [Instant Neural Graphics Primitives with a Multiresolution Hash Encoding](https://mlsanity.com/paper/2201.05989/) (2022)
- [Analyzing and Improving the Image Quality of StyleGAN](https://mlsanity.com/paper/1912.04958/) (2019)
- [DeepSDF: Learning Continuous Signed Distance Functions for Shape Representation](https://mlsanity.com/paper/1901.05103/) (2019)
- [Large Scale GAN Training for High Fidelity Natural Image Synthesis](https://mlsanity.com/paper/1809.11096/) (2018)
- [Implicit Neural Representations with Periodic Activation Functions](https://mlsanity.com/paper/2006.09661/) (2020)
- [Occupancy Networks: Learning 3D Reconstruction in Function Space](https://mlsanity.com/paper/1812.03828/) (2018)
- [Mip-NeRF 360: Unbounded Anti-Aliased Neural Radiance Fields](https://mlsanity.com/paper/2111.12077/) (2021)
- [Mip-NeRF: A Multiscale Representation for Anti-Aliasing Neural Radiance Fields](https://mlsanity.com/paper/2103.13415/) (2021)
- [Photo-Realistic Single Image Super-Resolution Using a Generative Adversarial Network](https://mlsanity.com/paper/1609.04802/) (2016)
- [NeuS: Learning Neural Implicit Surfaces by Volume Rendering for Multi-view Reconstruction](https://mlsanity.com/paper/2106.10689/) (2021)
- [Plenoxels: Radiance Fields without Neural Networks](https://mlsanity.com/paper/2112.05131/) (2021)
- [Enhanced Deep Residual Networks for Single Image Super-Resolution](https://mlsanity.com/paper/1707.02921/) (2017)
- [Demystifying MMD GANs](https://mlsanity.com/paper/1801.01401/) (2018)
- [Image Super-Resolution Using Very Deep Residual Channel Attention Networks](https://mlsanity.com/paper/1807.02758/) (2018)
- [ESRGAN: Enhanced Super-Resolution Generative Adversarial Networks](https://mlsanity.com/paper/1809.00219/) (2018)
- [NeRF in the Wild: Neural Radiance Fields for Unconstrained Photo Collections](https://mlsanity.com/paper/2008.02268/) (2020)
- [Image Super-Resolution Using Deep Convolutional Networks](https://mlsanity.com/paper/1501.00092/) (2014)
- [Efficient Geometry-aware 3D Generative Adversarial Networks](https://mlsanity.com/paper/2112.07945/) (2021)
- [Real-Time Single Image and Video Super-Resolution Using an Efficient Sub-Pixel Convolutional Neural Network](https://mlsanity.com/paper/1609.05158/) (2016)
- [Alias-Free Generative Adversarial Networks](https://mlsanity.com/paper/2106.12423/) (2021)
- [StarGAN v2: Diverse Image Synthesis for Multiple Domains](https://mlsanity.com/paper/1912.01865/) (2019)
- [Real-ESRGAN: Training Real-World Blind Super-Resolution with Pure Synthetic Data](https://mlsanity.com/paper/2107.10833/) (2021)
- [Neural Sparse Voxel Fields](https://mlsanity.com/paper/2007.11571/) (2020)
- [Scene Representation Networks: Continuous 3D-Structure-Aware Neural Scene Representations](https://mlsanity.com/paper/1906.01618/) (2019)
- [Residual Dense Network for Image Super-Resolution](https://mlsanity.com/paper/1802.08797/) (2018)
- [GIRAFFE: Representing Scenes as Compositional Generative Neural Feature Fields](https://mlsanity.com/paper/2011.12100/) (2020)
- [pi-GAN: Periodic Implicit Generative Adversarial Networks for 3D-Aware Image Synthesis](https://mlsanity.com/paper/2012.00926/) (2020)

## Built on by (most cited first, 30 of 73)

- [Rodin: A Generative Model for Sculpting 3D Digital Avatars Using Diffusion](https://mlsanity.com/paper/2212.06135/) (2022)
- [Generative Novel View Synthesis with 3D-Aware Diffusion Models](https://mlsanity.com/paper/2304.02602/) (2023)
- [EVA3D: Compositional 3D Human Generation from 2D Image Collections](https://mlsanity.com/paper/2210.04888/) (2022)
- [SceneDreamer: Unbounded 3D Scene Generation from 2D Image Collections](https://mlsanity.com/paper/2302.01330/) (2023)
- [3D-aware Image Generation using 2D Diffusion Models](https://mlsanity.com/paper/2303.17905/) (2023)
- [Real-Time Radiance Fields for Single-Image Portrait View Synthesis](https://mlsanity.com/paper/2305.02310/) (2023)
- [Consistent123: One Image to Highly Consistent 3D Asset Using Case-Aware Diffusion Priors](https://mlsanity.com/paper/2309.17261/) (2023)
- [ComboVerse: Compositional 3D Assets Creation Using Spatially-Aware Diffusion Guidance](https://mlsanity.com/paper/2403.12409/) (2024)
- [Portrait4D: Learning One-Shot 4D Head Avatar Synthesis using Synthetic Data](https://mlsanity.com/paper/2311.18729/) (2023)
- [StyleAvatar: Real-time Photo-realistic Portrait Avatar from a Single Video](https://mlsanity.com/paper/2305.00942/) (2023)
- [AniFaceGAN: Animatable 3D-Aware Face Image Generation for Video Avatars](https://mlsanity.com/paper/2210.06465/) (2022)
- [GaussianCube: A Structured and Explicit Radiance Representation for 3D Generative Modeling](https://mlsanity.com/paper/2403.19655/) (2024)
- [3D GAN Inversion with Pose Optimization](https://mlsanity.com/paper/2210.07301/) (2022)
- [3D GAN Inversion with Facial Symmetry Prior](https://mlsanity.com/paper/2211.16927/) (2022)
- [Preface: A Data-driven Volumetric Prior for Few-shot Ultra High-resolution Face Synthesis](https://mlsanity.com/paper/2309.16859/) (2023)
- [RodinHD: High-Fidelity 3D Avatar Generation with Diffusion Models](https://mlsanity.com/paper/2407.06938/) (2024)
- [OmniAvatar: Geometry-Guided Controllable 3D Head Synthesis](https://mlsanity.com/paper/2303.15539/) (2023)
- [PrimDiffusion: Volumetric Primitives Diffusion for 3D Human Generation](https://mlsanity.com/paper/2312.04559/) (2023)
- [HumanGen: Generating Human Radiance Fields with Explicit Priors](https://mlsanity.com/paper/2212.05321/) (2022)
- [VOODOO 3D: Volumetric Portrait Disentanglement for One-Shot 3D Head Reenactment](https://mlsanity.com/paper/2312.04651/) (2023)
- [Gaussian Variation Field Diffusion for High-fidelity Video-to-4D Synthesis](https://mlsanity.com/paper/2507.23785/) (2025)
- [State of the Art in Dense Monocular Non-Rigid 3D Reconstruction](https://mlsanity.com/paper/2210.15664/) (2022)
- [MEGANE: Morphable Eyeglass and Avatar Network](https://mlsanity.com/paper/2302.04868/) (2023)
- [3DFaceShop: Explicitly Controllable 3D-Aware Portrait Generation](https://mlsanity.com/paper/2209.05434/) (2022)
- [Local 3D Editing via 3D Distillation of CLIP Knowledge](https://mlsanity.com/paper/2306.12570/) (2023)
- [Local Implicit Ray Function for Generalizable Radiance Field Representation](https://mlsanity.com/paper/2304.12746/) (2023)
- [VOODOO XP: Expressive One-Shot Head Reenactment for VR Telepresence](https://mlsanity.com/paper/2405.16204/) (2024)
- [Mimic3D: Thriving 3D-Aware GANs via 3D-to-2D Imitation](https://mlsanity.com/paper/2303.09036/) (2023)
- [AniPortraitGAN: Animatable 3D Portrait Generation from 2D Image Collections](https://mlsanity.com/paper/2309.02186/) (2023)
- [Arc2Avatar: Generating Expressive 3D Avatars from a Single Image via ID Guidance](https://mlsanity.com/paper/2501.05379/) (2025)

## Abstract (arXiv)

Recent works have shown that 3D-aware GANs trained on unstructured single image collections can generate multiview images of novel instances. The key underpinnings to achieve this are a 3D radiance field generator and a volume rendering process. However, existing methods either cannot generate high-resolution images (e.g., up to 256X256) due to the high computation cost of neural volume rendering, or rely on 2D CNNs for image-space upsampling which jeopardizes the 3D consistency across different views. This paper proposes a novel 3D-aware GAN that can generate high resolution images (up to 1024X1024) while keeping strict 3D consistency as in volume rendering. Our motivation is to achieve super-resolution directly in the 3D space to preserve 3D consistency. We avoid the otherwise prohibitively-expensive computation cost by applying 2D convolutions on a set of 2D radiance manifolds defined in the recent generative radiance manifold (GRAM) approach, and apply dedicated loss functions for effective GAN training at high resolution. Experiments on FFHQ and AFHQv2 datasets show that our method can produce high-quality 3D-consistent results that significantly outperform existing methods. It makes a significant step towards closing the gap between traditional 2D image generation and 3D-consistent free-view generation.