mlsanityData to 7 Oct 2026

Structural Energy Guidance for View-Consistent Text-to-3D Generation

arXiv 2605.19876 ↗First posted 19 May 2026cs.CVcited by 0

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

Abstract (arXiv)

Text-to-3D generation based on diffusion models often suffers from the Janus problem, leading to inconsistent geometry across viewpoints. This work identifies viewpoint bias in 2D diffusion priors as the main cause and proposes Structural Energy-Guided Sampling (SEGS), a training-free and plug-and-play framework to improve multi-view consistency. SEGS constructs a structural energy in the PCA subspace of U-Net features and injects its gradient into the denoising process. It can be easily integrated into SDS/VSD pipelines without retraining. Experiments show that SEGS reduces the Janus Rate by about 10% on average and improves View-CS scores across multiple baselines, including DreamFusion, Magic3D, and LucidDreamer. This method effectively alleviates viewpoint artifacts while preserving appearance fidelity, providing a flexible solution for high-quality text-to-3D content generation.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Placed in 3D, point cloud and scene generation, one of 14 directions in Diffusion models. Builds on 37 of its 47 references that are in the map. First posted on arXiv 19 May 2026.

Builds on

37 of 47 references.

Closest ancestors · 13

Same direction, newest first

  1. 2023DreamControl: Control-Based Text-to-3D Generation with 3D Self-Prior11 Dec
  2. 2023Instant3D: Fast Text-to-3D with Sparse-View Generation and Large Reconstruction Model10 Nov
  3. 2023Control3D: Towards Controllable Text-to-3D Generation9 Nov
  4. 2023GaussianDreamer: Fast Generation from Text to 3D Gaussians by Bridging 2D and 3D Diffusion Models12 Oct
  5. 2023MVDream: Multi-view Diffusion for 3D Generation31 Aug
  6. 2023ProlificDreamer: High-Fidelity and Diverse Text-to-3D Generation with Variational Score Distillation25 May
  7. 2023DreamAvatar: Text-and-Shape Guided 3D Human Avatar Generation via Diffusion Models3 Apr
  8. 2023Debiasing Scores and Prompts of 2D Diffusion for View-consistent Text-to-3D Generation27 Mar
  9. 2023Fantasia3D: Disentangling Geometry and Appearance for High-quality Text-to-3D Content Creation24 Mar
  10. 2023Zero-1-to-3: Zero-shot One Image to 3D Object20 Mar
  11. 2022Point-E: A System for Generating 3D Point Clouds from Complex Prompts16 Dec
  12. 2022Magic3D: High-Resolution Text-to-3D Content Creation18 Nov
1 more
  1. 2022DreamFusion: Text-to-3D using 2D Diffusion29 Sep

Other references · 24

  1. 2021Learning Transferable Visual Models From Natural Language Supervisioncited by 33,456
  2. 2020Denoising Diffusion Probabilistic Modelscited by 20,851
  3. 2021High-Resolution Image Synthesis with Latent Diffusion Modelscited by 18,694
  4. 2020Denoising Diffusion Implicit Modelscited by 9,655
  5. 2020Score-Based Generative Modeling through Stochastic Differential Equationscited by 8,964
  6. 2021Diffusion Models Beat GANs on Image Synthesiscited by 8,185
  7. 20233D Gaussian Splatting for Real-Time Radiance Field Renderingcited by 6,141
  8. 2022LAION-5B: An open large-scale dataset for training next generation image-text modelscited by 4,131
  9. 2022Plug-and-Play Diffusion Features for Text-Driven Image-to-Image Translationcited by 897
  10. 2023DreamGaussian: Generative Gaussian Splatting for Efficient 3D Content Creationcited by 837
  11. 2023Objaverse-XL: A Universe of 10M+ 3D Objectscited by 767
  12. 2024LGM: Large Multi-View Gaussian Model for High-Resolution 3D Content Creationcited by 730
12 more
  1. 2022Latent-NeRF for Shape-Guided Generation of 3D Shapes and Texturescited by 506
  2. 2023Shap-E: Generating Conditional 3D Implicit Functionscited by 379
  3. 2023Diffusion Self-Guidance for Controllable Image Generationcited by 305
  4. 2023LucidDreamer: Towards High-Fidelity Text-to-3D Generation via Interval Score Matchingcited by 290
  5. 2023Re-imagine the Negative Prompt Algorithm: Transform 2D Diffusion into 3D, alleviate Janus problem and Beyondcited by 139
  6. 2023FreeControl: Training-Free Spatial Control of Any Text-to-Image Diffusion Model with Any Conditioncited by 89
  7. 2024Latent-based Diffusion Model for Long-tailed Recognitioncited by 14
  8. 2025Neural Radiance Fields for the Real World: A Surveycited by 12
  9. 2025GS-2DGS: Geometrically Supervised 2DGS for Reflective Object Reconstructioncited by 11
  10. 2024DGNS: Deformable Gaussian Splatting and Dynamic Neural Surface for Monocular Dynamic 3D Reconstructioncited by 7
  11. 2024Improving Viewpoint Consistency in 3D Generation via Structure Feature and CLIP Guidancecited by 2
  12. 2025Enhancing Features in Long-tailed Data Using Large Vision Modelcited by 2

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2025Structural Energy-Guided Sampling for View-Consistent Text-to-3D
  2. 2024JointDreamer: Ensuring Geometry Consistency and Text Congruence in Text-to-3D Generation via Joint Score Distillation
  3. 2024VividDreamer: Towards High-Fidelity and Efficient Text-to-3D Generation
  4. 2024Dual3D: Efficient and Consistent Text-to-3D Generation with Dual-mode Multi-view Latent Diffusion
  5. 2024ViewDiff: 3D-Consistent Image Generation with Text-to-Image Models
  6. 2023HiFA: High-fidelity Text-to-3D Generation with Advanced Diffusion Guidance
  7. 2024BoostDream: Efficient Refining for High-Quality Text-to-3D Generation from Multi-View Diffusion
  8. 2025Walking the Schr"odinger Bridge: A Direct Trajectory for Text-to-3D Generation