# Text-driven 3D Human Generation via Contrastive Preference Optimization

arXiv: https://arxiv.org/abs/2502.08977 · HTML: https://mlsanity.com/paper/2502.08977/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Placed in Diffusion and multimodal model alignment, one of 10 directions in LLM alignment / RLHF / preference optimisation.
- Builds on 39 of its 44 references that are in the map.
- First posted on arXiv 13 Feb 2025.

## Placed in

- LLM alignment / RLHF / preference optimisation / [Diffusion and multimodal model alignment](https://mlsanity.com/alignment/diffusion-and-multimodal-model-alignment/)

## Builds on (most cited first, 30 of 39)

- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [Photorealistic Text-to-Image Diffusion Models with Deep Language Understanding](https://mlsanity.com/paper/2205.11487/) (2022)
- [3D Gaussian Splatting for Real-Time Radiance Field Rendering](https://mlsanity.com/paper/2308.04079/) (2023)
- [Adding Conditional Control to Text-to-Image Diffusion Models](https://mlsanity.com/paper/2302.05543/) (2023)
- [DreamFusion: Text-to-3D using 2D Diffusion](https://mlsanity.com/paper/2209.14988/) (2022)
- [NeuS: Learning Neural Implicit Surfaces by Volume Rendering for Multi-view Reconstruction](https://mlsanity.com/paper/2106.10689/) (2021)
- [Expressive Body Capture: 3D Hands, Face, and Body from a Single Image](https://mlsanity.com/paper/1904.05866/) (2019)
- [Magic3D: High-Resolution Text-to-3D Content Creation](https://mlsanity.com/paper/2211.10440/) (2022)
- [ProlificDreamer: High-Fidelity and Diverse Text-to-3D Generation with Variational Score Distillation](https://mlsanity.com/paper/2305.16213/) (2023)
- [ImageReward: Learning and Evaluating Human Preferences for Text-to-Image Generation](https://mlsanity.com/paper/2304.05977/) (2023)
- [Pick-a-Pic: An Open Dataset of User Preferences for Text-to-Image Generation](https://mlsanity.com/paper/2305.01569/) (2023)
- [MVDream: Multi-view Diffusion for 3D Generation](https://mlsanity.com/paper/2308.16512/) (2023)
- [Human Preference Score v2: A Solid Benchmark for Evaluating Human Preferences of Text-to-Image Synthesis](https://mlsanity.com/paper/2306.09341/) (2023)
- [DreamGaussian: Generative Gaussian Splatting for Efficient 3D Content Creation](https://mlsanity.com/paper/2309.16653/) (2023)
- [Fantasia3D: Disentangling Geometry and Appearance for High-quality Text-to-3D Content Creation](https://mlsanity.com/paper/2303.13873/) (2023)
- [DensePose: Dense Human Pose Estimation In The Wild](https://mlsanity.com/paper/1802.00434/) (2018)
- [Deep Marching Tetrahedra: a Hybrid Representation for High-Resolution 3D Shape Synthesis](https://mlsanity.com/paper/2111.04276/) (2021)
- [CLIP-Mesh: Generating textured meshes from text using pretrained image-text models](https://mlsanity.com/paper/2203.13333/) (2022)
- [CLIP-Forge: Towards Zero-Shot Text-to-Shape Generation](https://mlsanity.com/paper/2110.02624/) (2021)
- [DreamAvatar: Text-and-Shape Guided 3D Human Avatar Generation via Diffusion Models](https://mlsanity.com/paper/2304.00916/) (2023)
- [TADA! Text to Animatable Digital Avatars](https://mlsanity.com/paper/2308.10899/) (2023)
- [LongAlign: A Recipe for Long Context Alignment of Large Language Models](https://mlsanity.com/paper/2401.18058/) (2024)
- [imGHUM: Implicit Generative Models of 3D Human Shape and Articulated Pose](https://mlsanity.com/paper/2108.10842/) (2021)
- [DreamHuman: Animatable 3D Avatars from Text](https://mlsanity.com/paper/2306.09329/) (2023)
- [HumanGaussian: Text-Driven 3D Human Generation with Gaussian Splatting](https://mlsanity.com/paper/2311.17061/) (2023)
- [HumanNorm: Learning Normal Diffusion Model for High-quality and Realistic 3D Human Generation](https://mlsanity.com/paper/2310.01406/) (2023)
- [AvatarCraft: Transforming Text into Neural Human Avatars with Parameterized Shape and Pose Control](https://mlsanity.com/paper/2303.17606/) (2023)
- [DreamWaltz: Make a Scene with Complex 3D Animatable Avatars](https://mlsanity.com/paper/2305.12529/) (2023)
- [GAvatar: Animatable 3D Gaussian Avatars with Implicit Mesh Learning](https://mlsanity.com/paper/2312.11461/) (2023)
- [3D Gaussian Splatting with Deferred Reflection](https://mlsanity.com/paper/2404.18454/) (2024)

## Built on by (most cited first, 1 of 1)

- [SMPL-GPTexture: Dual-View 3D Human Texture Estimation using Text-to-Image Generation Models](https://mlsanity.com/paper/2504.13378/) (2025)

## Abstract (arXiv)

Recent advances in Score Distillation Sampling (SDS) have improved 3D human generation from textual descriptions. However, existing methods still face challenges in accurately aligning 3D models with long and complex textual inputs. To address this challenge, we propose a novel framework that introduces contrastive preferences, where human-level preference models, guided by both positive and negative prompts, assist SDS for improved alignment. Specifically, we design a preference optimization module that integrates multiple models to comprehensively capture the full range of textual features. Furthermore, we introduce a negation preference module to mitigate over-optimization of irrelevant details by leveraging static-dynamic negation prompts, effectively preventing ``reward hacking". Extensive experiments demonstrate that our method achieves state-of-the-art results, significantly enhancing texture realism and visual alignment with textual descriptions, particularly for long and complex inputs.