# Debiasing Scores and Prompts of 2D Diffusion for View-consistent Text-to-3D Generation

arXiv: https://arxiv.org/abs/2303.15413 · HTML: https://mlsanity.com/paper/2303.15413/

## Key facts

- Cited by 32 papers in the map (data through 14 Oct 2026).
- Placed in 3D, point cloud and scene generation, one of 14 directions in Diffusion models.
- Builds on 23 of its 31 references that are in the map.
- First posted on arXiv 27 Mar 2023.

## Placed in

- Diffusion models / [3D, point cloud and scene generation](https://mlsanity.com/diffusion/3d-point-cloud-and-scene-generation/)

## Builds on (most cited first, 23 of 23)

- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [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)
- [Denoising Diffusion Implicit Models](https://mlsanity.com/paper/2010.02502/) (2020)
- [Score-Based Generative Modeling through Stochastic Differential Equations](https://mlsanity.com/paper/2011.13456/) (2020)
- [Diffusion Models Beat GANs on Image Synthesis](https://mlsanity.com/paper/2105.05233/) (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)
- [Classifier-Free Diffusion Guidance](https://mlsanity.com/paper/2207.12598/) (2022)
- [Generative Modeling by Estimating Gradients of the Data Distribution](https://mlsanity.com/paper/1907.05600/) (2019)
- [Improved Denoising Diffusion Probabilistic Models](https://mlsanity.com/paper/2102.09672/) (2021)
- [GLIDE: Towards Photorealistic Image Generation and Editing with Text-Guided Diffusion Models](https://mlsanity.com/paper/2112.10741/) (2021)
- [Elucidating the Design Space of Diffusion-Based Generative Models](https://mlsanity.com/paper/2206.00364/) (2022)
- [DreamFusion: Text-to-3D using 2D Diffusion](https://mlsanity.com/paper/2209.14988/) (2022)
- [Zero-1-to-3: Zero-shot One Image to 3D Object](https://mlsanity.com/paper/2303.11328/) (2023)
- [Magic3D: High-Resolution Text-to-3D Content Creation](https://mlsanity.com/paper/2211.10440/) (2022)
- [NeRF in the Wild: Neural Radiance Fields for Unconstrained Photo Collections](https://mlsanity.com/paper/2008.02268/) (2020)
- [Score Jacobian Chaining: Lifting Pretrained 2D Diffusion Models for 3D Generation](https://mlsanity.com/paper/2212.00774/) (2022)
- [Zero-Shot Text-Guided Object Generation with Dream Fields](https://mlsanity.com/paper/2112.01455/) (2021)
- [Latent-NeRF for Shape-Guided Generation of 3D Shapes and Textures](https://mlsanity.com/paper/2211.07600/) (2022)
- [Improving Sample Quality of Diffusion Models Using Self-Attention Guidance](https://mlsanity.com/paper/2210.00939/) (2022)
- [Let 2D Diffusion Model Know 3D-Consistency for Robust Text-to-3D Generation](https://mlsanity.com/paper/2303.07937/) (2023)

## Built on by (most cited first, 30 of 32)

- [Smoothed Energy Guidance: Guiding Diffusion Models with Reduced Energy Curvature of Attention](https://mlsanity.com/paper/2408.00760/) (2024)
- [Hyper-3DG: Text-to-3D Gaussian Generation via Hypergraph](https://mlsanity.com/paper/2403.09236/) (2024)
- [TetSphere Splatting: Representing High-Quality Geometry with Lagrangian Volumetric Meshes](https://mlsanity.com/paper/2405.20283/) (2024)
- [Atlas3D: Physically Constrained Self-Supporting Text-to-3D for Simulation and Fabrication](https://mlsanity.com/paper/2405.18515/) (2024)
- [DreamComposer: Controllable 3D Object Generation via Multi-View Conditions](https://mlsanity.com/paper/2312.03611/) (2023)
- [A Survey On Text-to-3D Contents Generation In The Wild](https://mlsanity.com/paper/2405.09431/) (2024)
- [Localized Gaussian Splatting Editing with Contextual Awareness](https://mlsanity.com/paper/2408.00083/) (2024)
- [RecDreamer: Consistent Text-to-3D Generation via Uniform Score Distillation](https://mlsanity.com/paper/2502.12640/) (2025)
- [DreamDissector: Learning Disentangled Text-to-3D Generation from 2D Diffusion Priors](https://mlsanity.com/paper/2407.16260/) (2024)
- [TV-3DG: Mastering Text-to-3D Customized Generation with Visual Prompt](https://mlsanity.com/paper/2410.21299/) (2024)
- [Benchmarking and Learning Multi-Dimensional Quality Evaluator for Text-to-3D Generation](https://mlsanity.com/paper/2412.11170/) (2024)
- [Geometry-Aware Score Distillation via 3D Consistent Noising and Gradient Consistency Modeling](https://mlsanity.com/paper/2406.16695/) (2024)
- [DreamMapping: High-Fidelity Text-to-3D Generation via Variational Distribution Mapping](https://mlsanity.com/paper/2409.05099/) (2024)
- [Fully Bayesian Differential Gaussian Processes through Stochastic Differential Equations](https://mlsanity.com/paper/2408.06069/) (2024)
- [RewardSDS: Aligning Score Distillation via Reward-Weighted Sampling](https://mlsanity.com/paper/2503.09601/) (2025)
- [How I Met Your Bias: Investigating Bias Amplification in Diffusion Models](https://mlsanity.com/paper/2512.20233/) (2025)
- [BiMotion: B-spline Motion for Text-guided Dynamic 3D Character Generation](https://mlsanity.com/paper/2602.18873/) (2026)
- [Perturb-and-Revise: Flexible 3D Editing with Generative Trajectories](https://mlsanity.com/paper/2412.05279/) (2024)
- [ConsDreamer: Advancing Multi-View Consistency for Zero-Shot Text-to-3D Generation](https://mlsanity.com/paper/2504.02316/) (2025)
- [OrientDream: Streamlining Text-to-3D Generation with Explicit Orientation Control](https://mlsanity.com/paper/2406.10000/) (2024)
- [Improving Viewpoint Consistency in 3D Generation via Structure Feature and CLIP Guidance](https://mlsanity.com/paper/2412.02287/) (2024)
- [Track, Inpaint, Resplat: Subject-driven 3D and 4D Generation with Progressive Texture Infilling](https://mlsanity.com/paper/2510.23605/) (2025)
- [Text-Image Conditioned Diffusion for Consistent Text-to-3D Generation](https://mlsanity.com/paper/2312.11774/) (2023)
- [Text2VDM: Text to Vector Displacement Maps for Expressive and Interactive 3D Sculpting](https://mlsanity.com/paper/2502.20045/) (2025)
- [Point Cloud Compression and Objective Quality Assessment: A Survey](https://mlsanity.com/paper/2506.22902/) (2025)
- [Structural Energy-Guided Sampling for View-Consistent Text-to-3D](https://mlsanity.com/paper/2508.16917/) (2025)
- [Debiasing Diffusion Priors via 3D Attention for Consistent Gaussian Splatting](https://mlsanity.com/paper/2512.07345/) (2025)
- [Harnessing the Power of Training-Free Techniques in Text-to-2D Generation for Text-to-3D Generation via Score Distillation Sampling](https://mlsanity.com/paper/2505.19868/) (2025)
- [Structural Energy Guidance for View-Consistent Text-to-3D Generation](https://mlsanity.com/paper/2605.19876/) (2026)
- [Controllable Dynamic 3D Shape Generation via 3D Trajectories and Text](https://mlsanity.com/paper/2606.05162/) (2026)

## Abstract (arXiv)

Existing score-distilling text-to-3D generation techniques, despite their considerable promise, often encounter the view inconsistency problem. One of the most notable issues is the Janus problem, where the most canonical view of an object (textite.g., face or head) appears in other views. In this work, we explore existing frameworks for score-distilling text-to-3D generation and identify the main causes of the view inconsistency problem -- the embedded bias of 2D diffusion models. Based on these findings, we propose two approaches to debias the score-distillation frameworks for view-consistent text-to-3D generation. Our first approach, called score debiasing, involves cutting off the score estimated by 2D diffusion models and gradually increasing the truncation value throughout the optimization process. Our second approach, called prompt debiasing, identifies conflicting words between user prompts and view prompts using a language model, and adjusts the discrepancy between view prompts and the viewing direction of an object. Our experimental results show that our methods improve the realism of the generated 3D objects by significantly reducing artifacts and achieve a good trade-off between faithfulness to the 2D diffusion models and 3D consistency with little overhead. Our project page is available at~urlhttps://susunghong.github.io/Debiased-Score-Distillation-Sampling/.