mlsanityData to 14 Oct 2026

Hash3D: Training-free Acceleration for 3D Generation

arXiv 2404.06091 ↗First posted 9 Apr 2024cs.CVcited by 19

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

Abstract (arXiv)

The evolution of 3D generative modeling has been notably propelled by the adoption of 2D diffusion models. Despite this progress, the cumbersome optimization process per se presents a critical hurdle to efficiency. In this paper, we introduce Hash3D, a universal acceleration for 3D generation without model training. Central to Hash3D is the insight that feature-map redundancy is prevalent in images rendered from camera positions and diffusion time-steps in close proximity. By effectively hashing and reusing these feature maps across neighboring timesteps and camera angles, Hash3D substantially prevents redundant calculations, thus accelerating the diffusion model's inference in 3D generation tasks. We achieve this through an adaptive grid-based hashing. Surprisingly, this feature-sharing mechanism not only speed up the generation but also enhances the smoothness and view consistency of the synthesized 3D objects. Our experiments covering 5 text-to-3D and 3 image-to-3D models, demonstrate Hash3D's versatility to speed up optimization, enhancing efficiency by 1.3 to 4 times. Additionally, Hash3D's integration with 3D Gaussian splatting largely speeds up 3D model creation, reducing text-to-3D processing to about 10 minutes and image-to-3D conversion to roughly 30 seconds. The project page is at https://adamdad.github.io/hash3D/.

Key facts. Cited by 19 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 51 of its 62 references that are in the map. First posted on arXiv 9 Apr 2024.

Builds on

51 of 62 references.

Closest ancestors · 15

Same direction, newest first

  1. 2024EscherNet: A Generative Model for Scalable View Synthesis6 Feb
  2. 2023ET3D: Efficient Text-to-3D Generation via Multi-View Distillation27 Nov
  3. 2023Instant3D: Fast Text-to-3D with Sparse-View Generation and Large Reconstruction Model10 Nov
  4. 2023GaussianDreamer: Fast Generation from Text to 3D Gaussians by Bridging 2D and 3D Diffusion Models12 Oct
  5. 2023SyncDreamer: Generating Multiview-consistent Images from a Single-view Image7 Sep
  6. 2023Magic123: One Image to High-Quality 3D Object Generation Using Both 2D and 3D Diffusion Priors30 Jun
  7. 2023One-2-3-45: Any Single Image to 3D Mesh in 45 Seconds without Per-Shape Optimization29 Jun
  8. 2023ProlificDreamer: High-Fidelity and Diverse Text-to-3D Generation with Variational Score Distillation25 May
  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. 2022Score Jacobian Chaining: Lifting Pretrained 2D Diffusion Models for 3D Generation1 Dec
3 more
  1. 20223D Neural Field Generation using Triplane Diffusion30 Nov
  2. 2022Magic3D: High-Resolution Text-to-3D Content Creation18 Nov
  3. 2022DreamFusion: Text-to-3D using 2D Diffusion29 Sep

Other references · 36

  1. 2021Learning Transferable Visual Models From Natural Language Supervisioncited by 33,744
  2. 2015U-Net: Convolutional Networks for Biomedical Image Segmentationcited by 19,713
  3. 2021High-Resolution Image Synthesis with Latent Diffusion Modelscited by 18,863
  4. 2018The Unreasonable Effectiveness of Deep Features as a Perceptual Metriccited by 11,177
  5. 2020Denoising Diffusion Implicit Modelscited by 9,781
  6. 2022Photorealistic Text-to-Image Diffusion Models with Deep Language Understandingcited by 6,355
  7. 20233D Gaussian Splatting for Real-Time Radiance Field Renderingcited by 6,226
  8. 2019Generative Modeling by Estimating Gradients of the Data Distributioncited by 4,101
  9. 2022Instant Neural Graphics Primitives with a Multiresolution Hash Encodingcited by 3,723
  10. 2022DPM-Solver: A Fast ODE Solver for Diffusion Probabilistic Model Sampling in Around 10 Stepscited by 1,979
  11. 2023Consistency Modelscited by 1,822
  12. 2020Reformer: The Efficient Transformercited by 1,668
24 more
  1. 2023DreamGaussian: Generative Gaussian Splatting for Efficient 3D Content Creationcited by 843
  2. 2022Pseudo Numerical Methods for Diffusion Models on Manifoldscited by 700
  3. 2022Google Scanned Objects: A High-Quality Dataset of 3D Scanned Household Itemscited by 612
  4. 2016Learning a Probabilistic Latent Space of Object Shapes via 3D Generative-Adversarial Modelingcited by 558
  5. 2022Latent-NeRF for Shape-Guided Generation of 3D Shapes and Texturescited by 506
  6. 2021Deep Marching Tetrahedra: a Hybrid Representation for High-Resolution 3D Shape Synthesiscited by 460
  7. 2023Shap-E: Generating Conditional 3D Implicit Functionscited by 385
  8. 2023DeepCache: Accelerating Diffusion Models for Freecited by 359
  9. 2022Analytic-DPM: an Analytic Estimate of the Optimal Reverse Variance in Diffusion Probabilistic Modelscited by 334
  10. 2021Hash Layers For Large Sparse Modelscited by 237
  11. 2023DMV3D: Denoising Multi-View Diffusion using 3D Large Reconstruction Modelcited by 214
  12. 2023Structural Pruning for Diffusion Modelscited by 195
  13. 2023DreamGaussian4D: Generative 4D Gaussian Splattingcited by 194
  14. 2023Cache Me if You Can: Accelerating Diffusion Models through Block Cachingcited by 151
  15. 2015Compressing Neural Networks with the Hashing Trickcited by 150
  16. 2023Re-imagine the Negative Prompt Algorithm: Transform 2D Diffusion into 3D, alleviate Janus problem and Beyondcited by 139
  17. 2017HashNet: Deep Learning to Hash by Continuationcited by 122
  18. 2022Diffusion Probabilistic Model Made Slimcited by 121
  19. 2023Anything-3D: Towards Single-view Anything Reconstruction in the Wildcited by 92
  20. 2015Simultaneous Feature Learning and Hash Coding with Deep Neural Networkscited by 44
  21. 2017Deep Supervised Discrete Hashingcited by 36
  22. 2023Faster Diffusion: Rethinking the Role of the Encoder for Diffusion Model Inferencecited by 34
  23. 2023SHACIRA: Scalable HAsh-grid Compression for Implicit Neural Representationscited by 31
  24. 2023HollowNeRF: Pruning Hashgrid-Based NeRFs with Trainable Collision Mitigationcited by 16

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2024: 7; 2025: 8; 2026: 4.

19 papers.

Sort:

By area:

  1. 2025dKV-Cache: The Cache for Diffusion Language Modelscited by 143
  2. 2024Learning-to-Cache: Accelerating Diffusion Transformer via Layer Cachingcited by 142
  3. 2024FlashSplat: 2D to 3D Gaussian Splatting Segmentation Solved Optimallycited by 58
  4. 2024Collaborative Decoding Makes Visual Auto-Regressive Modeling Efficientcited by 33
  5. 2024AsyncDiff: Parallelizing Diffusion Models by Asynchronous Denoisingcited by 22
  6. 2025Memory-Efficient Visual Autoregressive Modeling with Scale-Aware KV Cache Compressioncited by 22
  7. 2025A Survey on 3D Gaussian Splatting Applications: Segmentation, Editing, and Generationcited by 19
  8. 2025A Survey on Cache Methods in Diffusion Models: Toward Efficient Multi-Modal Generationcited by 16
  9. 2024A General Framework to Boost 3D GS Initialization for Text-to-3D Generation by Lexical Richnesscited by 8
  10. 2025Digital Twin Generation from Visual Data: A Surveycited by 7
  11. 2026BiMotion: B-spline Motion for Text-guided Dynamic 3D Character Generationcited by 4
  12. 2025Fast3Dcache: Training-free 3D Geometry Synthesis Accelerationcited by 3
7 more
  1. 2026Fast-SAM3D: 3Dfy Anything in Images but Fastercited by 3
  2. 2024Vista3D: Unravel the 3D Darkside of a Single Imagecited by 1
  3. 2025Bridging Geometry-Coherent Text-to-3D Generation with Multi-View Diffusion Priors and Gaussian Splattingcited by 1
  4. 2026THOM: Generating Physically Plausible Hand-Object Meshes From Textcited by 1
  5. 2024Focus on Neighbors and Know the Whole: Towards Consistent Dense Multiview Text-to-Image Generator for 3D Creationcited by 0
  6. 2025Sphinx: Efficiently Serving Novel View Synthesis using Regression-Guided Selective Refinementcited by 0
  7. 2026GeoCache: Training-Free Acceleration of Multi-View Texture Diffusion via Geometric Delta Transportcited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2025Bolt3D: Generating 3D Scenes in Seconds
  2. 2024Hunyuan3D 1.0: A Unified Framework for Text-to-3D and Image-to-3D Generation
  3. 2023One-2-3-45++: Fast Single Image to 3D Objects with Consistent Multi-View Generation and 3D Diffusion
  4. 2024Direct3D: Scalable Image-to-3D Generation via 3D Latent Diffusion Transformer
  5. 2024BoostDream: Efficient Refining for High-Quality Text-to-3D Generation from Multi-View Diffusion
  6. 2024Enhancing Single Image to 3D Generation using Gaussian Splatting and Hybrid Diffusion Priors
  7. 2024Ouroboros3D: Image-to-3D Generation via 3D-aware Recursive Diffusion
  8. 2024Sculpt3D: Multi-View Consistent Text-to-3D Generation with Sparse 3D Prior