mlsanityData to 7 Oct 2026

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

arXiv 2303.15413 ↗First posted 27 Mar 2023cs.CV cs.CL cs.GRcited by 32

On the map: Diffusion models → 3D, point cloud and scene generation

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/.

Key facts. Cited by 32 papers in the map (data through 7 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.

Builds on

23 of 31 references.

Closest ancestors · 5

Same direction, newest first

  1. 2023Zero-1-to-3: Zero-shot One Image to 3D Object20 Mar
  2. 2023Let 2D Diffusion Model Know 3D-Consistency for Robust Text-to-3D Generation14 Mar
  3. 2022Score Jacobian Chaining: Lifting Pretrained 2D Diffusion Models for 3D Generation1 Dec
  4. 2022Magic3D: High-Resolution Text-to-3D Content Creation18 Nov
  5. 2022DreamFusion: Text-to-3D using 2D Diffusion29 Sep

Other references · 18

  1. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,204
  2. 2020Denoising Diffusion Probabilistic Modelscited by 20,851
  3. 2021High-Resolution Image Synthesis with Latent Diffusion Modelscited by 18,694
  4. 2018The Unreasonable Effectiveness of Deep Features as a Perceptual Metriccited by 11,029
  5. 2020Denoising Diffusion Implicit Modelscited by 9,655
  6. 2020Score-Based Generative Modeling through Stochastic Differential Equationscited by 8,964
  7. 2021Diffusion Models Beat GANs on Image Synthesiscited by 8,185
  8. 2022Hierarchical Text-Conditional Image Generation with CLIP Latentscited by 6,539
  9. 2022Photorealistic Text-to-Image Diffusion Models with Deep Language Understandingcited by 6,322
  10. 2022Classifier-Free Diffusion Guidancecited by 5,717
  11. 2019Generative Modeling by Estimating Gradients of the Data Distributioncited by 4,067
  12. 2021Improved Denoising Diffusion Probabilistic Modelscited by 3,736
6 more
  1. 2021GLIDE: Towards Photorealistic Image Generation and Editing with Text-Guided Diffusion Modelscited by 3,595
  2. 2022Elucidating the Design Space of Diffusion-Based Generative Modelscited by 2,994
  3. 2020NeRF in the Wild: Neural Radiance Fields for Unconstrained Photo Collectionscited by 1,230
  4. 2021Zero-Shot Text-Guided Object Generation with Dream Fieldscited by 513
  5. 2022Latent-NeRF for Shape-Guided Generation of 3D Shapes and Texturescited by 506
  6. 2022Improving Sample Quality of Diffusion Models Using Self-Attention Guidancecited by 151

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2023: 2; 2024: 15; 2025: 10; 2026: 5.

32 papers.

Sort:

By area:

  1. 2024Smoothed Energy Guidance: Guiding Diffusion Models with Reduced Energy Curvature of Attentioncited by 55
  2. 2024Hyper-3DG: Text-to-3D Gaussian Generation via Hypergraphcited by 21
  3. 2024TetSphere Splatting: Representing High-Quality Geometry with Lagrangian Volumetric Meshescited by 20
  4. 2024Atlas3D: Physically Constrained Self-Supporting Text-to-3D for Simulation and Fabricationcited by 19
  5. 2023DreamComposer: Controllable 3D Object Generation via Multi-View Conditionscited by 18
  6. 2024A Survey On Text-to-3D Contents Generation In The Wildcited by 13
  7. 2024Localized Gaussian Splatting Editing with Contextual Awarenesscited by 13
  8. 2025RecDreamer: Consistent Text-to-3D Generation via Uniform Score Distillationcited by 9
  9. 2024DreamDissector: Learning Disentangled Text-to-3D Generation from 2D Diffusion Priorscited by 8
  10. 2024TV-3DG: Mastering Text-to-3D Customized Generation with Visual Promptcited by 8
  11. 2024Benchmarking and Learning Multi-Dimensional Quality Evaluator for Text-to-3D Generationcited by 7
  12. 2024Geometry-Aware Score Distillation via 3D Consistent Noising and Gradient Consistency Modelingcited by 6
20 more
  1. 2024DreamMapping: High-Fidelity Text-to-3D Generation via Variational Distribution Mappingcited by 5
  2. 2024Fully Bayesian Differential Gaussian Processes through Stochastic Differential Equationscited by 4
  3. 2025RewardSDS: Aligning Score Distillation via Reward-Weighted Samplingcited by 4
  4. 2025How I Met Your Bias: Investigating Bias Amplification in Diffusion Modelscited by 4
  5. 2026BiMotion: B-spline Motion for Text-guided Dynamic 3D Character Generationcited by 4
  6. 2024OrientDream: Streamlining Text-to-3D Generation with Explicit Orientation Controlcited by 2
  7. 2024Improving Viewpoint Consistency in 3D Generation via Structure Feature and CLIP Guidancecited by 2
  8. 2024Perturb-and-Revise: Flexible 3D Editing with Generative Trajectoriescited by 2
  9. 2025ConsDreamer: Advancing Multi-View Consistency for Zero-Shot Text-to-3D Generationcited by 2
  10. 2025Track, Inpaint, Resplat: Subject-driven 3D and 4D Generation with Progressive Texture Infillingcited by 2
  11. 2023Text-Image Conditioned Diffusion for Consistent Text-to-3D Generationcited by 1
  12. 2025Text2VDM: Text to Vector Displacement Maps for Expressive and Interactive 3D Sculptingcited by 1
  13. 2025Point Cloud Compression and Objective Quality Assessment: A Surveycited by 1
  14. 2025Structural Energy-Guided Sampling for View-Consistent Text-to-3Dcited by 1
  15. 2025Debiasing Diffusion Priors via 3D Attention for Consistent Gaussian Splattingcited by 1
  16. 2025Harnessing the Power of Training-Free Techniques in Text-to-2D Generation for Text-to-3D Generation via Score Distillation Samplingcited by 0
  17. 2026Structural Energy Guidance for View-Consistent Text-to-3D Generationcited by 0
  18. 2026Controllable Dynamic 3D Shape Generation via 3D Trajectories and Textcited by 0
  19. 2026Vitality-Aware Compression for Efficient Image-to-Shape Diffusion Transformerscited by 0
  20. 2026Hallo4D: Multi-Modal Hallucination Mitigation for Consistent Spatio-Temporal Generationcited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2024JointDreamer: Ensuring Geometry Consistency and Text Congruence in Text-to-3D Generation via Joint Score Distillation
  2. 2023MVDream: Multi-view Diffusion for 3D Generation
  3. 2025Dive3D: Diverse Distillation-based Text-to-3D Generation via Score Implicit Matching
  4. 2023T3Bench: Benchmarking Current Progress in Text-to-3D Generation
  5. 2025Vision-Language Models as Differentiable Semantic and Spatial Rewards for Text-to-3D Generation
  6. 2024Retrieval-Augmented Score Distillation for Text-to-3D Generation
  7. 2024VividDreamer: Towards High-Fidelity and Efficient Text-to-3D Generation
  8. 2024A Quantitative Evaluation of Score Distillation Sampling Based Text-to-3D