# DreamDPO: Aligning Text-to-3D Generation with Human Preferences via Direct Preference Optimization

arXiv: https://arxiv.org/abs/2502.04370 · HTML: https://mlsanity.com/paper/2502.04370/

## Key facts

- Cited by 27 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 37 of its 92 references that are in the map.
- First posted on arXiv 5 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 37)

- [DINOv2: Learning Robust Visual Features without Supervision](https://mlsanity.com/paper/2304.07193/) (2023)
- [Classifier-Free Diffusion Guidance](https://mlsanity.com/paper/2207.12598/) (2022)
- [Training a Helpful and Harmless Assistant with Reinforcement Learning from Human Feedback](https://mlsanity.com/paper/2204.05862/) (2022)
- [GLIDE: Towards Photorealistic Image Generation and Editing with Text-Guided Diffusion Models](https://mlsanity.com/paper/2112.10741/) (2021)
- [DreamBooth: Fine Tuning Text-to-Image Diffusion Models for Subject-Driven Generation](https://mlsanity.com/paper/2208.12242/) (2022)
- [Constitutional AI: Harmlessness from AI Feedback](https://mlsanity.com/paper/2212.08073/) (2022)
- [DreamFusion: Text-to-3D using 2D Diffusion](https://mlsanity.com/paper/2209.14988/) (2022)
- [An Image is Worth One Word: Personalizing Text-to-Image Generation using Textual Inversion](https://mlsanity.com/paper/2208.01618/) (2022)
- [Qwen-VL: A Versatile Vision-Language Model for Understanding, Localization, Text Reading, and Beyond](https://mlsanity.com/paper/2308.12966/) (2023)
- [Imagen Video: High Definition Video Generation with Diffusion Models](https://mlsanity.com/paper/2210.02303/) (2022)
- [ProlificDreamer: High-Fidelity and Diverse Text-to-3D Generation with Variational Score Distillation](https://mlsanity.com/paper/2305.16213/) (2023)
- [Training Diffusion Models with Reinforcement Learning](https://mlsanity.com/paper/2305.13301/) (2023)
- [SimPO: Simple Preference Optimization with a Reference-Free Reward](https://mlsanity.com/paper/2405.14734/) (2024)
- [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)
- [Aligning Large Multimodal Models with Factually Augmented RLHF](https://mlsanity.com/paper/2309.14525/) (2023)
- [Point-E: A System for Generating 3D Point Clouds from Complex Prompts](https://mlsanity.com/paper/2212.08751/) (2022)
- [The Dawn of LMMs: Preliminary Explorations with GPT-4V(ision)](https://mlsanity.com/paper/2309.17421/) (2023)
- [SyncDreamer: Generating Multiview-consistent Images from a Single-view Image](https://mlsanity.com/paper/2309.03453/) (2023)
- [Directly Fine-Tuning Diffusion Models on Differentiable Rewards](https://mlsanity.com/paper/2309.17400/) (2023)
- [Aligning Text-to-Image Models using Human Feedback](https://mlsanity.com/paper/2302.12192/) (2023)
- [Shap-E: Generating Conditional 3D Implicit Functions](https://mlsanity.com/paper/2305.02463/) (2023)
- [Instant3D: Fast Text-to-3D with Sparse-View Generation and Large Reconstruction Model](https://mlsanity.com/paper/2311.06214/) (2023)
- [Text-to-image Diffusion Models in Generative AI: A Survey](https://mlsanity.com/paper/2303.07909/) (2023)
- [Text2Room: Extracting Textured 3D Meshes from 2D Text-to-Image Models](https://mlsanity.com/paper/2303.11989/) (2023)
- [DreamAvatar: Text-and-Shape Guided 3D Human Avatar Generation via Diffusion Models](https://mlsanity.com/paper/2304.00916/) (2023)
- [RLAIF-V: Open-Source AI Feedback Leads to Super GPT-4V Trustworthiness](https://mlsanity.com/paper/2405.17220/) (2024)
- [Text-to-3D with Classifier Score Distillation](https://mlsanity.com/paper/2310.19415/) (2023)
- [HiFA: High-fidelity Text-to-3D Generation with Advanced Diffusion Guidance](https://mlsanity.com/paper/2305.18766/) (2023)

## Built on by (most cited first, 27 of 27)

- [The Landscape of Agentic Reinforcement Learning for LLMs: A Survey](https://mlsanity.com/paper/2509.02547/) (2025)
- [DSO: Aligning 3D Generators with Simulation Feedback for Physical Soundness](https://mlsanity.com/paper/2503.22677/) (2025)
- [MPO: Multilingual Safety Alignment via Reward Gap Optimization](https://mlsanity.com/paper/2505.16869/) (2025)
- [MagicID: Hybrid Preference Optimization for ID-Consistent and Dynamic-Preserved Video Customization](https://mlsanity.com/paper/2503.12689/) (2025)
- [VINCIE: Unlocking In-context Image Editing from Video](https://mlsanity.com/paper/2506.10941/) (2025)
- [Integrating Reinforcement Learning with Visual Generative Models: Foundations and Advances](https://mlsanity.com/paper/2508.10316/) (2025)
- [Nabla-R2D3: Effective and Efficient 3D Diffusion Alignment with 2D Rewards](https://mlsanity.com/paper/2506.15684/) (2025)
- [Zero-1-to-A: Zero-Shot One Image to Animatable Head Avatars Using Video Diffusion](https://mlsanity.com/paper/2503.15851/) (2025)
- [Reinforcement Learning for Large Model: A Survey](https://mlsanity.com/paper/2508.08189/) (2025)
- [AnchorFlow: Training-Free 3D Editing via Latent Anchor-Aligned Flows](https://mlsanity.com/paper/2511.22357/) (2025)
- [DreamCS: Geometry-Aware Text-to-3D Generation with Unpaired 3D Reward Supervision](https://mlsanity.com/paper/2506.09814/) (2025)
- [EvolvingGrasp: Evolutionary Grasp Generation via Efficient Preference Alignment](https://mlsanity.com/paper/2503.14329/) (2025)
- [Vision-Language Models as Differentiable Semantic and Spatial Rewards for Text-to-3D Generation](https://mlsanity.com/paper/2509.15772/) (2025)
- [Extending Visual Dynamics for Video-to-Music Generation](https://mlsanity.com/paper/2504.07594/) (2025)
- [Reinforced Strategy Optimization for Conversational Recommender Systems via Network-of-Experts](https://mlsanity.com/paper/2509.26093/) (2025)
- [Stroke3D: Lifting 2D strokes into rigged 3D model via latent diffusion models](https://mlsanity.com/paper/2602.09713/) (2026)
- [Preference Score Distillation: Leveraging 2D Rewards to Align Text-to-3D Generation with Human Preference](https://mlsanity.com/paper/2603.01594/) (2026)
- [BrickAnything: Geometry-Conditioned Buildable Brick Generation with Structure-Aware Tokenization](https://mlsanity.com/paper/2605.26182/) (2026)
- [A Cross-Model VLM-Judge Protocol for Single-Image 3D Mesh Quality (and Why Cheap Proxies Fall Short)](https://mlsanity.com/paper/2606.18451/) (2026)
- [Point Cloud Compression and Objective Quality Assessment: A Survey](https://mlsanity.com/paper/2506.22902/) (2025)
- [Let Language Constrain Geometry: Vision-Language Models as Semantic and Spatial Critics for 3D Generation](https://mlsanity.com/paper/2511.14271/) (2025)
- [iARCS: Iterative Agentic RL for Controllable 3D Scene Generation](https://mlsanity.com/paper/2608.06161/) (2026)
- [HandDreamer: Zero-Shot Text to 3D Hand Model Generation using Corrective Hand Shape Guidance](https://mlsanity.com/paper/2604.04425/) (2026)
- [Distributed Direct Preference Optimization](https://mlsanity.com/paper/2605.20696/) (2026)
- [Judging to Improve: A De-biased VLM-as-3D-Judge Protocol for Single-Image 3D Generation](https://mlsanity.com/paper/2606.20364/) (2026)
- [Sculpting NeRF Geometry: Human-Preference Fine-Tuning of a 3D-Aware Face GAN](https://mlsanity.com/paper/2606.27305/) (2026)
- [Learn from the Gap: Differential-Aware Advantage Pruning with Adaptive Rollout Sampling for GRPO](https://mlsanity.com/paper/2609.36932/) (2026)

## Abstract (arXiv)

Text-to-3D generation automates 3D content creation from textual descriptions, which offers transformative potential across various fields. However, existing methods often struggle to align generated content with human preferences, limiting their applicability and flexibility. To address these limitations, in this paper, we propose DreamDPO, an optimization-based framework that integrates human preferences into the 3D generation process, through direct preference optimization. Practically, DreamDPO first constructs pairwise examples, then compare their alignment with human preferences using reward or large multimodal models, and lastly optimizes the 3D representation with a preference-driven loss function. By leveraging pairwise comparison to reflect preferences, DreamDPO reduces reliance on precise pointwise quality evaluations while enabling fine-grained controllability through preference-guided optimization. Experiments demonstrate that DreamDPO achieves competitive results, and provides higher-quality and more controllable 3D content compared to existing methods. The code and models will be open-sourced.