mlsanityData to 7 Oct 2026

G3DR: Generative 3D Reconstruction in ImageNet

arXiv 2403.00939 ↗First posted 1 Mar 2024cs.CV cs.GRcited by 5

Not on the map. Why?

Abstract (arXiv)

We introduce a novel 3D generative method, Generative 3D Reconstruction (G3DR) in ImageNet, capable of generating diverse and high-quality 3D objects from single images, addressing the limitations of existing methods. At the heart of our framework is a novel depth regularization technique that enables the generation of scenes with high-geometric fidelity. G3DR also leverages a pretrained language-vision model, such as CLIP, to enable reconstruction in novel views and improve the visual realism of generations. Additionally, G3DR designs a simple but effective sampling procedure to further improve the quality of generations. G3DR offers diverse and efficient 3D asset generation based on class or text conditioning. Despite its simplicity, G3DR is able to beat state-of-theart methods, improving over them by up to 22% in perceptual metrics and 90% in geometry scores, while needing only half of the training time. Code is available at https://github.com/preddy5/G3DR

Key facts. Cited by 5 papers in the map (data through 7 Oct 2026). Builds on 59 of its 67 references that are in the map. First posted on arXiv 1 Mar 2024.

Builds on

59 of 67 references.

References · 59

  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. 2018The Unreasonable Effectiveness of Deep Features as a Perceptual Metriccited by 11,029
  5. 2021Diffusion Models Beat GANs on Image Synthesiscited by 8,185
  6. 2016SGDR: Stochastic Gradient Descent with Warm Restartscited by 4,993
  7. 2022DreamFusion: Text-to-3D using 2D Diffusioncited by 3,006
  8. 2016Improved Techniques for Training GANscited by 2,938
  9. 2018Large Scale GAN Training for High Fidelity Natural Image Synthesiscited by 2,609
  10. 2015LSUN: Construction of a Large-scale Image Dataset using Deep Learning with Humans in the Loopcited by 1,350
  11. 2018Image Super-Resolution Using Very Deep Residual Channel Attention Networkscited by 1,256
  12. 2021Efficient Geometry-aware 3D Generative Adversarial Networkscited by 1,204
38 more
  1. 2020GIRAFFE: Representing Scenes as Compositional Generative Neural Feature Fieldscited by 784
  2. 2023K-Planes: Explicit Radiance Fields in Space, Time, and Appearancecited by 742
  3. 2021Depth-supervised NeRF: Fewer Views and Faster Training for Freecited by 732
  4. 2020pi-GAN: Periodic Implicit Generative Adversarial Networks for 3D-Aware Image Synthesiscited by 708
  5. 2022Autoregressive Image Generation using Residual Quantizationcited by 706
  6. 2020GRAF: Generative Radiance Fields for 3D-Aware Image Synthesiscited by 688
  7. 2021RegNeRF: Regularizing Neural Radiance Fields for View Synthesis from Sparse Inputscited by 614
  8. 2021Zero-Shot Text-Guided Object Generation with Dream Fieldscited by 513
  9. 2022StyleGAN-XL: Scaling StyleGAN to Large Diverse Datasetscited by 489
  10. 2021StyleNeRF: A Style-based 3D-Aware Generator for High-resolution Image Synthesiscited by 477
  11. 2022MonoSDF: Exploring Monocular Geometric Cues for Neural Implicit Surface Reconstructioncited by 467
  12. 2021Putting NeRF on a Diet: Semantically Consistent Few-Shot View Synthesiscited by 464
  13. 2021Neural Geometric Level of Detail: Real-time Rendering with Implicit 3D Shapescited by 426
  14. 2021CLIP-NeRF: Text-and-Image Driven Manipulation of Neural Radiance Fieldscited by 369
  15. 2021Dense Depth Priors for Neural Radiance Fields from Sparse Input Viewscited by 301
  16. 2021StyleSDF: High-Resolution 3D-Consistent Image and Geometry Generationcited by 289
  17. 20223D Neural Field Generation using Triplane Diffusioncited by 274
  18. 2021GRAM: Generative Radiance Manifolds for 3D-Aware Image Generationcited by 216
  19. 20203D Photography using Context-aware Layered Depth Inpaintingcited by 206
  20. 2022RenderDiffusion: Image Diffusion for 3D Reconstruction, Inpainting and Generationcited by 162
  21. 2023HyperDiffusion: Generating Implicit Neural Fields with Weight-Space Diffusioncited by 152
  22. 2021CIPS-3D: A 3D-Aware Generator of GANs Based on Conditionally-Independent Pixel Synthesiscited by 149
  23. 2023Tri-MipRF: Tri-Mip Representation for Efficient Anti-Aliasing Neural Radiance Fieldscited by 142
  24. 2022VoxGRAF: Fast 3D-Aware Image Synthesis with Sparse Voxel Gridscited by 133
  25. 2021Unconstrained Scene Generation with Locally Conditioned Radiance Fieldscited by 130
  26. 2021NeRF-VAE: A Geometry Aware 3D Scene Generative Modelcited by 111
  27. 20213D-aware Image Synthesis via Learning Structural and Textural Representationscited by 109
  28. 2022EpiGRAF: Rethinking training of 3D GANscited by 108
  29. 2023HoloDiffusion: Training a 3D Diffusion Model using 2D Imagescited by 106
  30. 2021Boosting Monocular Depth Estimation Models to High-Resolution via Content-Adaptive Multi-Resolution Mergingcited by 104
  31. 2022GIRAFFE HD: A High-Resolution 3D-aware Generative Modelcited by 86
  32. 2021LOLNeRF: Learn from One Lookcited by 84
  33. 2022Pix2NeRF: Unsupervised Conditional π-GAN for Single Image to Neural Radiance Fields Translationcited by 73
  34. 20233D-aware Image Generation using 2D Diffusion Modelscited by 69
  35. 2020Lifting 2D StyleGAN for 3D-Aware Face Generationcited by 64
  36. 2023LDM3D: Latent Diffusion Model for 3Dcited by 53
  37. 20233D generation on ImageNetcited by 47
  38. 2022Multi-View Consistent Generative Adversarial Networks for 3D-aware Image Synthesiscited by 43

50 most cited of 59 All 59 (JSON)

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2024: 3; 2025: 1; 2026: 1.

5 papers.

  1. 2024Wavelet Latent Diffusion (Wala): Billion-Parameter 3D Generative Model with Compact Wavelet Encodingscited by 10
  2. 2025F3D-Gaus: Feed-forward 3D-aware Generation on ImageNet with Cycle-Aggregative Gaussian Splattingcited by 3
  3. 20243D-WAG: Hierarchical Wavelet-Guided Autoregressive Generation for High-Fidelity 3D Shapescited by 2
  4. 2024Towards High-Fidelity 3D Portrait Generation with Rich Details by Cross-View Prior-Aware Diffusioncited by 1
  5. 2026One View Is Enough: In-the-Wild Monocular Pretraining for Novel View Generationcited by 0