mlsanityData to 7 Oct 2026

Diffusion Time-step Curriculum for One Image to 3D Generation

arXiv 2404.04562 ↗First posted 6 Apr 2024cs.CVcited by 20

Not on the map. Why?

Abstract (arXiv)

Score distillation sampling~(SDS) has been widely adopted to overcome the absence of unseen views in reconstructing 3D objects from a single image. It leverages pre-trained 2D diffusion models as teacher to guide the reconstruction of student 3D models. Despite their remarkable success, SDS-based methods often encounter geometric artifacts and texture saturation. We find out the crux is the overlooked indiscriminate treatment of diffusion time-steps during optimization: it unreasonably treats the student-teacher knowledge distillation to be equal at all time-steps and thus entangles coarse-grained and fine-grained modeling. Therefore, we propose the Diffusion Time-step Curriculum one-image-to-3D pipeline (DTC123), which involves both the teacher and student models collaborating with the time-step curriculum in a coarse-to-fine manner. Extensive experiments on NeRF4, RealFusion15, GSO and Level50 benchmark demonstrate that DTC123 can produce multi-view consistent, high-quality, and diverse 3D assets. Codes and more generation demos will be released in https://github.com/yxymessi/DTC123.

Key facts. Cited by 20 papers in the map (data through 7 Oct 2026). Builds on 63 of its 77 references that are in the map. First posted on arXiv 6 Apr 2024.

Builds on

63 of 77 references.

References · 63

  1. 2020Denoising Diffusion Probabilistic Modelscited by 20,851
  2. 2021High-Resolution Image Synthesis with Latent Diffusion Modelscited by 18,694
  3. 2020Denoising Diffusion Implicit Modelscited by 9,655
  4. 2020Score-Based Generative Modeling through Stochastic Differential Equationscited by 8,964
  5. 2022Photorealistic Text-to-Image Diffusion Models with Deep Language Understandingcited by 6,322
  6. 20233D Gaussian Splatting for Real-Time Radiance Field Renderingcited by 6,141
  7. 2023BLIP-2: Bootstrapping Language-Image Pre-training with Frozen Image Encoders and Large Language Modelscited by 6,069
  8. 2022Classifier-Free Diffusion Guidancecited by 5,717
  9. 2022Instant Neural Graphics Primitives with a Multiresolution Hash Encodingcited by 3,698
  10. 2014Deep Learning Face Attributes in the Wildcited by 3,679
  11. 2022DreamFusion: Text-to-3D using 2D Diffusioncited by 3,006
  12. 2022Elucidating the Design Space of Diffusion-Based Generative Modelscited by 2,994
38 more
  1. 2022An Image is Worth One Word: Personalizing Text-to-Image Generation using Textual Inversioncited by 2,231
  2. 2021Mip-NeRF: A Multiscale Representation for Anti-Aliasing Neural Radiance Fieldscited by 1,957
  3. 2021Vision Transformers for Dense Predictioncited by 1,789
  4. 2021NeuS: Learning Neural Implicit Surfaces by Volume Rendering for Multi-view Reconstructioncited by 1,701
  5. 2022Objaverse: A Universe of Annotated 3D Objectscited by 1,522
  6. 2023Zero-1-to-3: Zero-shot One Image to 3D Objectcited by 1,483
  7. 2022Magic3D: High-Resolution Text-to-3D Content Creationcited by 1,285
  8. 2023ProlificDreamer: High-Fidelity and Diverse Text-to-3D Generation with Variational Score Distillationcited by 1,207
  9. 2021Direct Voxel Grid Optimization: Super-fast Convergence for Radiance Fields Reconstructioncited by 961
  10. 2023MVDream: Multi-view Diffusion for 3D Generationcited by 928
  11. 2023DreamGaussian: Generative Gaussian Splatting for Efficient 3D Content Creationcited by 837
  12. 2023Fantasia3D: Disentangling Geometry and Appearance for High-quality Text-to-3D Content Creationcited by 684
  13. 2023SyncDreamer: Generating Multiview-consistent Images from a Single-view Imagecited by 638
  14. 2022Google Scanned Objects: A High-Quality Dataset of 3D Scanned Household Itemscited by 601
  15. 2022Score Jacobian Chaining: Lifting Pretrained 2D Diffusion Models for 3D Generationcited by 597
  16. 2023One-2-3-45: Any Single Image to 3D Mesh in 45 Seconds without Per-Shape Optimizationcited by 555
  17. 2022Latent-NeRF for Shape-Guided Generation of 3D Shapes and Texturescited by 506
  18. 2022MonoSDF: Exploring Monocular Geometric Cues for Neural Implicit Surface Reconstructioncited by 467
  19. 2021Deep Marching Tetrahedra: a Hybrid Representation for High-Resolution 3D Shape Synthesiscited by 459
  20. 2017Neural 3D Mesh Renderercited by 437
  21. 2023Magic123: One Image to High-Quality 3D Object Generation Using Both 2D and 3D Diffusion Priorscited by 395
  22. 2019SynSin: End-to-end View Synthesis from a Single Imagecited by 364
  23. 2023Make-It-3D: High-Fidelity 3D Creation from A Single Image with Diffusion Priorcited by 341
  24. 2023OmniObject3D: Large-Vocabulary 3D Object Dataset for Realistic Perception, Reconstruction and Generationcited by 324
  25. 2022NeuS2: Fast Learning of Neural Implicit Surfaces for Multi-view Reconstructioncited by 311
  26. 2023RealFusion: 360deg Reconstruction of Any Object from a Single Imagecited by 305
  27. 2023Text-to-image Diffusion Models in Generative AI: A Surveycited by 264
  28. 2022Diffusion models as plug-and-play priorscited by 230
  29. 2022Adan: Adaptive Nesterov Momentum Algorithm for Faster Optimizing Deep Modelscited by 172
  30. 2020Stable View Synthesiscited by 165
  31. 2022NeRF: Neural Radiance Field in 3D Vision: A Comprehensive Review (Updated Post-Gaussian Splatting)cited by 156
  32. 2022NeRDi: Single-View NeRF Synthesis with Language-Guided Diffusion as General Image Priorscited by 156
  33. 2022NeuralLift-360: Lifting An In-the-wild 2D Photo to A 3D Object with 360deg Viewscited by 148
  34. 2023Re-imagine the Negative Prompt Algorithm: Transform 2D Diffusion into 3D, alleviate Janus problem and Beyondcited by 139
  35. 2023SweetDreamer: Aligning Geometric Priors in 2D Diffusion for Consistent Text-to-3Dcited by 134
  36. 2023HiFA: High-fidelity Text-to-3D Generation with Advanced Diffusion Guidancecited by 109
  37. 2023Noise-Free Score Distillationcited by 99
  38. 2023Consistent123: Improve Consistency for One Image to 3D Object Synthesiscited by 84

50 most cited of 63 All 63 (JSON)

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2024: 11; 2025: 7; 2026: 2.

20 papers.

Sort:

By area:

  1. 2024FlashSplat: 2D to 3D Gaussian Splatting Segmentation Solved Optimallycited by 57
  2. 2024Meissonic: Revitalizing Masked Generative Transformers for Efficient High-Resolution Text-to-Image Synthesiscited by 55
  3. 2024SplatFlow: Multi-View Rectified Flow Model for 3D Gaussian Splatting Synthesiscited by 34
  4. 2024HumanEdit: A High-Quality Human-Rewarded Dataset for Instruction-based Image Editingcited by 29
  5. 2024MVGamba: Unify 3D Content Generation as State Space Sequence Modelingcited by 23
  6. 2024Atlas3D: Physically Constrained Self-Supporting Text-to-3D for Simulation and Fabricationcited by 19
  7. 2025Nautilus: Locality-aware Autoencoder for Scalable Mesh Generationcited by 18
  8. 2025VideoAuteur: Towards Long Narrative Video Generationcited by 17
  9. 2025Unified Dense Prediction of Video Diffusioncited by 13
  10. 2024TrAME: Trajectory-Anchored Multi-View Editing for Text-Guided 3D Gaussian Splatting Manipulationcited by 10
  11. 2025Seeing World Dynamics in a Nutshellcited by 7
  12. 2024Few-shot NeRF by Adaptive Rendering Loss Regularizationcited by 6
8 more
  1. 2025UltraFlux: Data-Model Co-Design for High-quality Native 4K Text-to-Image Generation across Diverse Aspect Ratioscited by 6
  2. 2024Bootstrap3D: Improving Multi-view Diffusion Model with Synthetic Datacited by 5
  3. 2024Pushing Rendering Boundaries: Hard Gaussian Splattingcited by 3
  4. 2025Distilling Multi-view Diffusion Models into 3D Generatorscited by 3
  5. 2025Personalize Your Gaussian: Consistent 3D Scene Personalization from a Single Imagecited by 2
  6. 2024Vista3D: Unravel the 3D Darkside of a Single Imagecited by 1
  7. 2026MVAnimate: Enhancing Character Animation with Multi-View Optimizationcited by 1
  8. 2026Memory-Efficient Fine-Tuning Diffusion Transformers via Dynamic Patch Sampling and Block Skippingcited by 1

Similar, not cited

Close in wording, no citation either way

  1. 2023DreamTime: An Improved Optimization Strategy for Diffusion-Guided 3D Generation
  2. 2023RL Dreams: Policy Gradient Optimization for Score Distillation based 3D Generation
  3. 2024Diverse Score Distillation
  4. 2023DreamCraft3D: Hierarchical 3D Generation with Bootstrapped Diffusion Prior
  5. 2024Score Distillation via Reparametrized DDIM
  6. 2024Diffusion Models Are Innate One-Step Generators
  7. 2026Variance Reduction on the Camera Axis: Multi-View Score Distillation for 3D
  8. 2024Diffusion2: Dynamic 3D Content Generation via Score Composition of Video and Multi-view Diffusion Models