# Understanding Pure CLIP Guidance for Voxel Grid NeRF Models

arXiv: https://arxiv.org/abs/2209.15172 · HTML: https://mlsanity.com/paper/2209.15172/

## Key facts

- Cited by 56 papers in the map (data through 14 Oct 2026).
- Builds on 37 of its 41 references that are in the map.
- First posted on arXiv 30 Sep 2022.

## Builds on (most cited first, 30 of 37)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [High-Resolution Image Synthesis with Latent Diffusion Models](https://mlsanity.com/paper/2112.10752/) (2021)
- [Hierarchical Text-Conditional Image Generation with CLIP Latents](https://mlsanity.com/paper/2204.06125/) (2022)
- [Photorealistic Text-to-Image Diffusion Models with Deep Language Understanding](https://mlsanity.com/paper/2205.11487/) (2022)
- [Zero-Shot Text-to-Image Generation](https://mlsanity.com/paper/2102.12092/) (2021)
- [Instant Neural Graphics Primitives with a Multiresolution Hash Encoding](https://mlsanity.com/paper/2201.05989/) (2022)
- [GLIDE: Towards Photorealistic Image Generation and Editing with Text-Guided Diffusion Models](https://mlsanity.com/paper/2112.10741/) (2021)
- [Mip-NeRF: A Multiscale Representation for Anti-Aliasing Neural Radiance Fields](https://mlsanity.com/paper/2103.13415/) (2021)
- [Plenoxels: Radiance Fields without Neural Networks](https://mlsanity.com/paper/2112.05131/) (2021)
- [LAION-400M: Open Dataset of CLIP-Filtered 400 Million Image-Text Pairs](https://mlsanity.com/paper/2111.02114/) (2021)
- [Scaling Autoregressive Models for Content-Rich Text-to-Image Generation](https://mlsanity.com/paper/2206.10789/) (2022)
- [TensoRF: Tensorial Radiance Fields](https://mlsanity.com/paper/2203.09517/) (2022)
- [Direct Voxel Grid Optimization: Super-fast Convergence for Radiance Fields Reconstruction](https://mlsanity.com/paper/2111.11215/) (2021)
- [Neural Sparse Voxel Fields](https://mlsanity.com/paper/2007.11571/) (2020)
- [PlenOctrees for Real-time Rendering of Neural Radiance Fields](https://mlsanity.com/paper/2103.14024/) (2021)
- [CogView: Mastering Text-to-Image Generation via Transformers](https://mlsanity.com/paper/2105.13290/) (2021)
- [KiloNeRF: Speeding up Neural Radiance Fields with Thousands of Tiny MLPs](https://mlsanity.com/paper/2103.13744/) (2021)
- [LiT: Zero-Shot Transfer with Locked-image text Tuning](https://mlsanity.com/paper/2111.07991/) (2021)
- [Zero-Shot Text-Guided Object Generation with Dream Fields](https://mlsanity.com/paper/2112.01455/) (2021)
- [FastNeRF: High-Fidelity Neural Rendering at 200FPS](https://mlsanity.com/paper/2103.10380/) (2021)
- [Baking Neural Radiance Fields for Real-Time View Synthesis](https://mlsanity.com/paper/2103.14645/) (2021)
- [SLIP: Self-supervision meets Language-Image Pre-training](https://mlsanity.com/paper/2112.12750/) (2021)
- [CLIP-NeRF: Text-and-Image Driven Manipulation of Neural Radiance Fields](https://mlsanity.com/paper/2112.05139/) (2021)
- [Differentiable Augmentation for Data-Efficient GAN Training](https://mlsanity.com/paper/2006.10738/) (2020)
- [Text2Mesh: Text-Driven Neural Stylization for Meshes](https://mlsanity.com/paper/2112.03221/) (2021)
- [CogView2: Faster and Better Text-to-Image Generation via Hierarchical Transformers](https://mlsanity.com/paper/2204.14217/) (2022)
- [VQGAN-CLIP: Open Domain Image Generation and Editing with Natural Language Guidance](https://mlsanity.com/paper/2204.08583/) (2022)
- [CLIP-Mesh: Generating textured meshes from text using pretrained image-text models](https://mlsanity.com/paper/2203.13333/) (2022)

## Built on by (most cited first, 30 of 56)

- [Score Jacobian Chaining: Lifting Pretrained 2D Diffusion Models for 3D Generation](https://mlsanity.com/paper/2212.00774/) (2022)
- [One-2-3-45: Any Single Image to 3D Mesh in 45 Seconds without Per-Shape Optimization](https://mlsanity.com/paper/2306.16928/) (2023)
- [Instruct-NeRF2NeRF: Editing 3D Scenes with Instructions](https://mlsanity.com/paper/2303.12789/) (2023)
- [Make-It-3D: High-Fidelity 3D Creation from A Single Image with Diffusion Prior](https://mlsanity.com/paper/2303.14184/) (2023)
- [One-2-3-45++: Fast Single Image to 3D Objects with Consistent Multi-View Generation and 3D Diffusion](https://mlsanity.com/paper/2311.07885/) (2023)
- [Text2Room: Extracting Textured 3D Meshes from 2D Text-to-Image Models](https://mlsanity.com/paper/2303.11989/) (2023)
- [OpenShape: Scaling Up 3D Shape Representation Towards Open-World Understanding](https://mlsanity.com/paper/2305.10764/) (2023)
- [3DGen: Triplane Latent Diffusion for Textured Mesh Generation](https://mlsanity.com/paper/2303.05371/) (2023)
- [DreamCraft3D: Hierarchical 3D Generation with Bootstrapped Diffusion Prior](https://mlsanity.com/paper/2310.16818/) (2023)
- [Dream3D: Zero-Shot Text-to-3D Synthesis Using 3D Shape Prior and Text-to-Image Diffusion Models](https://mlsanity.com/paper/2212.14704/) (2022)
- [Alpha-CLIP: A CLIP Model Focusing on Wherever You Want](https://mlsanity.com/paper/2312.03818/) (2023)
- [Text2NeRF: Text-Driven 3D Scene Generation with Neural Radiance Fields](https://mlsanity.com/paper/2305.11588/) (2023)
- [Animate124: Animating One Image to 4D Dynamic Scene](https://mlsanity.com/paper/2311.14603/) (2023)
- [AvatarCraft: Transforming Text into Neural Human Avatars with Parameterized Shape and Pose Control](https://mlsanity.com/paper/2303.17606/) (2023)
- [Advances in 3D Generation: A Survey](https://mlsanity.com/paper/2401.17807/) (2024)
- [SC4D: Sparse-Controlled Video-to-4D Generation and Motion Transfer](https://mlsanity.com/paper/2404.03736/) (2024)
- [CompoNeRF: Text-guided Multi-object Compositional NeRF with Editable 3D Scene Layout](https://mlsanity.com/paper/2303.13843/) (2023)
- [MeshFormer: High-Quality Mesh Generation with 3D-Guided Reconstruction Model](https://mlsanity.com/paper/2408.10198/) (2024)
- [Instant3D: Instant Text-to-3D Generation](https://mlsanity.com/paper/2311.08403/) (2023)
- [Text2Immersion: Generative Immersive Scene with 3D Gaussians](https://mlsanity.com/paper/2312.09242/) (2023)
- [Points-to-3D: Bridging the Gap between Sparse Points and Shape-Controllable Text-to-3D Generation](https://mlsanity.com/paper/2307.13908/) (2023)
- [X-Mesh: Towards Fast and Accurate Text-driven 3D Stylization via Dynamic Textual Guidance](https://mlsanity.com/paper/2303.15764/) (2023)
- [3D Paintbrush: Local Stylization of 3D Shapes with Cascaded Score Distillation](https://mlsanity.com/paper/2311.09571/) (2023)
- [SpaRP: Fast 3D Object Reconstruction and Pose Estimation from Sparse Views](https://mlsanity.com/paper/2408.10195/) (2024)
- [TAPS3D: Text-Guided 3D Textured Shape Generation from Pseudo Supervision](https://mlsanity.com/paper/2303.13273/) (2023)
- [Blending-NeRF: Text-Driven Localized Editing in Neural Radiance Fields](https://mlsanity.com/paper/2308.11974/) (2023)
- [InterFusion: Text-Driven Generation of 3D Human-Object Interaction](https://mlsanity.com/paper/2403.15612/) (2024)
- [DreamCraft: Text-Guided Generation of Functional 3D Environments in Minecraft](https://mlsanity.com/paper/2404.15538/) (2024)
- [InNeRF360: Text-Guided 3D-Consistent Object Inpainting on 360-degree Neural Radiance Fields](https://mlsanity.com/paper/2305.15094/) (2023)
- [BeNeRF: Neural Radiance Fields from a Single Blurry Image and Event Stream](https://mlsanity.com/paper/2407.02174/) (2024)

## Abstract (arXiv)

We explore the task of text to 3D object generation using CLIP. Specifically, we use CLIP for guidance without access to any datasets, a setting we refer to as pure CLIP guidance. While prior work has adopted this setting, there is no systematic study of mechanics for preventing adversarial generations within CLIP. We illustrate how different image-based augmentations prevent the adversarial generation problem, and how the generated results are impacted. We test different CLIP model architectures and show that ensembling different models for guidance can prevent adversarial generations within bigger models and generate sharper results. Furthermore, we implement an implicit voxel grid model to show how neural networks provide an additional layer of regularization, resulting in better geometrical structure and coherency of generated objects. Compared to prior work, we achieve more coherent results with higher memory efficiency and faster training speeds.