# Text2Light: Zero-Shot Text-Driven HDR Panorama Generation

arXiv: https://arxiv.org/abs/2209.09898 · HTML: https://mlsanity.com/paper/2209.09898/

## Key facts

- Cited by 24 papers in the map (data through 14 Oct 2026).
- Builds on 50 of its 61 references that are in the map.
- First posted on arXiv 20 Sep 2022.

## Builds on (most cited first, 30 of 50)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [Denoising Diffusion Probabilistic Models](https://mlsanity.com/paper/2006.11239/) (2020)
- [High-Resolution Image Synthesis with Latent Diffusion Models](https://mlsanity.com/paper/2112.10752/) (2021)
- [The Unreasonable Effectiveness of Deep Features as a Perceptual Metric](https://mlsanity.com/paper/1801.03924/) (2018)
- [Hierarchical Text-Conditional Image Generation with CLIP Latents](https://mlsanity.com/paper/2204.06125/) (2022)
- [A Style-Based Generator Architecture for Generative Adversarial Networks](https://mlsanity.com/paper/1812.04948/) (2018)
- [Neural Discrete Representation Learning](https://mlsanity.com/paper/1711.00937/) (2017)
- [Image-to-Image Translation with Conditional Adversarial Networks](https://mlsanity.com/paper/1611.07004/) (2016)
- [Zero-Shot Text-to-Image Generation](https://mlsanity.com/paper/2102.12092/) (2021)
- [GLIDE: Towards Photorealistic Image Generation and Editing with Text-Guided Diffusion Models](https://mlsanity.com/paper/2112.10741/) (2021)
- [Analyzing and Improving the Image Quality of StyleGAN](https://mlsanity.com/paper/1912.04958/) (2019)
- [Taming Transformers for High-Resolution Image Synthesis](https://mlsanity.com/paper/2012.09841/) (2020)
- [Improved Techniques for Training GANs](https://mlsanity.com/paper/1606.03498/) (2016)
- [Enhanced Deep Residual Networks for Single Image Super-Resolution](https://mlsanity.com/paper/1707.02921/) (2017)
- [Generating Diverse High-Fidelity Images with VQ-VAE-2](https://mlsanity.com/paper/1906.00446/) (2019)
- [On the Spectral Bias of Neural Networks](https://mlsanity.com/paper/1806.08734/) (2018)
- [Training Generative Adversarial Networks with Limited Data](https://mlsanity.com/paper/2006.06676/) (2020)
- [Alias-Free Generative Adversarial Networks](https://mlsanity.com/paper/2106.12423/) (2021)
- [MaskGIT: Masked Generative Image Transformer](https://mlsanity.com/paper/2202.04200/) (2022)
- [StyleCLIP: Text-Driven Manipulation of StyleGAN Imagery](https://mlsanity.com/paper/2103.17249/) (2021)
- [CogView: Mastering Text-to-Image Generation via Transformers](https://mlsanity.com/paper/2105.13290/) (2021)
- [HDR image reconstruction from a single exposure using deep CNNs](https://mlsanity.com/paper/1710.07480/) (2017)
- [Learning to Predict Indoor Illumination from a Single Image](https://mlsanity.com/paper/1704.00090/) (2017)
- [Single-Image HDR Reconstruction by Learning to Reverse the Camera Pipeline](https://mlsanity.com/paper/2004.01179/) (2020)
- [LAFITE: Towards Language-Free Training for Text-to-Image Generation](https://mlsanity.com/paper/2111.13792/) (2021)
- [ExpandNet: A Deep Convolutional Neural Network for High Dynamic Range Expansion from Low Dynamic Range Content](https://mlsanity.com/paper/1803.02266/) (2018)
- [Unleashing Transformers: Parallel Token Prediction with Discrete Absorbing Diffusion for Fast High-Resolution Image Generation from Vector-Quantized Codes](https://mlsanity.com/paper/2111.12701/) (2021)
- [FuseDream: Training-Free Text-to-Image Generation with Improved CLIP+GAN Space Optimization](https://mlsanity.com/paper/2112.01573/) (2021)

## Built on by (most cited first, 24 of 24)

- [CLIP for All Things Zero-Shot Sketch-Based Image Retrieval, Fine-Grained or Not](https://mlsanity.com/paper/2303.13440/) (2023)
- [DiffusionLight: Light Probes for Free by Painting a Chrome Ball](https://mlsanity.com/paper/2312.09168/) (2023)
- [Ctrl-Room: Controllable Text-to-3D Room Meshes Generation with Layout Constraints](https://mlsanity.com/paper/2310.03602/) (2023)
- [LayerPano3D: Layered 3D Panorama for Hyper-Immersive Scene Generation](https://mlsanity.com/paper/2408.13252/) (2024)
- [Customizing 360-Degree Panoramas through Text-to-Image Diffusion Models](https://mlsanity.com/paper/2310.18840/) (2023)
- [360-Degree Panorama Generation from Few Unregistered NFoV Images](https://mlsanity.com/paper/2308.14686/) (2023)
- [3D-SceneDreamer: Text-Driven 3D-Consistent Scene Generation](https://mlsanity.com/paper/2403.09439/) (2024)
- [A Survey of Representation Learning, Optimization Strategies, and Applications for Omnidirectional Vision](https://mlsanity.com/paper/2502.10444/) (2025)
- [3D Scene Generation: A Survey](https://mlsanity.com/paper/2505.05474/) (2025)
- [Text2Scene: Text-driven Indoor Scene Stylization with Part-aware Details](https://mlsanity.com/paper/2308.16880/) (2023)
- [AIGCOIQA2024: Perceptual Quality Assessment of AI Generated Omnidirectional Images](https://mlsanity.com/paper/2404.01024/) (2024)
- [Bracket Diffusion: HDR Image Generation by Consistent LDR Denoising](https://mlsanity.com/paper/2405.14304/) (2024)
- [Panorama Generation From NFoV Image Done Right](https://mlsanity.com/paper/2503.18420/) (2025)
- [HoloTime: Taming Video Diffusion Models for Panoramic 4D Scene Generation](https://mlsanity.com/paper/2504.21650/) (2025)
- [Omni2: Unifying Omnidirectional Image Generation and Editing in an Omni Model](https://mlsanity.com/paper/2504.11379/) (2025)
- [LDM3D-VR: Latent Diffusion Model for 3D VR](https://mlsanity.com/paper/2311.03226/) (2023)
- [Semantic Aware Diffusion Inverse Tone Mapping](https://mlsanity.com/paper/2405.15468/) (2024)
- [OmniDrag: Enabling Motion Control for Omnidirectional Image-to-Video Generation](https://mlsanity.com/paper/2412.09623/) (2024)
- [Generating 360deg Video is What You Need For a 3D Scene](https://mlsanity.com/paper/2504.02045/) (2025)
- [360PanT: Training-Free Text-Driven 360-Degree Panorama-to-Panorama Translation](https://mlsanity.com/paper/2409.08397/) (2024)
- [iControl3D: An Interactive System for Controllable 3D Scene Generation](https://mlsanity.com/paper/2408.01678/) (2024)
- [SpaceBlender: Creating Context-Rich Collaborative Spaces Through Generative 3D Scene Blending](https://mlsanity.com/paper/2409.13926/) (2024)
- [DreamAnywhere: Object-Centric Panoramic 3D Scene Generation](https://mlsanity.com/paper/2506.20367/) (2025)
- [Towards Physically-Based Sky-Modeling For Image Based Lighting](https://mlsanity.com/paper/2512.15632/) (2025)

## Abstract (arXiv)

High-quality HDRIs(High Dynamic Range Images), typically HDR panoramas, are one of the most popular ways to create photorealistic lighting and 360-degree reflections of 3D scenes in graphics. Given the difficulty of capturing HDRIs, a versatile and controllable generative model is highly desired, where layman users can intuitively control the generation process. However, existing state-of-the-art methods still struggle to synthesize high-quality panoramas for complex scenes. In this work, we propose a zero-shot text-driven framework, Text2Light, to generate 4K+ resolution HDRIs without paired training data. Given a free-form text as the description of the scene, we synthesize the corresponding HDRI with two dedicated steps: 1) text-driven panorama generation in low dynamic range(LDR) and low resolution, and 2) super-resolution inverse tone mapping to scale up the LDR panorama both in resolution and dynamic range. Specifically, to achieve zero-shot text-driven panorama generation, we first build dual codebooks as the discrete representation for diverse environmental textures. Then, driven by the pre-trained CLIP model, a text-conditioned global sampler learns to sample holistic semantics from the global codebook according to the input text. Furthermore, a structure-aware local sampler learns to synthesize LDR panoramas patch-by-patch, guided by holistic semantics. To achieve super-resolution inverse tone mapping, we derive a continuous representation of 360-degree imaging from the LDR panorama as a set of structured latent codes anchored to the sphere. This continuous representation enables a versatile module to upscale the resolution and dynamic range simultaneously. Extensive experiments demonstrate the superior capability of Text2Light in generating high-quality HDR panoramas. In addition, we show the feasibility of our work in realistic rendering and immersive VR.