mlsanityData to 7 Oct 2026

Multi-View Large Reconstruction Model via Geometry-Aware Positional Encoding and Attention

arXiv 2406.07648 ↗First posted 11 Jun 2024cs.CVcited by 6

Not on the map. Why?

Abstract (arXiv)

Despite recent advancements in the Large Reconstruction Model (LRM) demonstrating impressive results, when extending its input from single image to multiple images, it exhibits inefficiencies, subpar geometric and texture quality, as well as slower convergence speed than expected. It is attributed to that, LRM formulates 3D reconstruction as a naive images-to-3D translation problem, ignoring the strong 3D coherence among the input images. In this paper, we propose a Multi-view Large Reconstruction Model (M-LRM) designed to reconstruct high-quality 3D shapes from multi-views in a 3D-aware manner. Specifically, we introduce a multi-view consistent cross-attention scheme to enable M-LRM to accurately query information from the input images. Moreover, we employ the 3D priors of the input multi-view images to initialize the triplane tokens. Compared to previous methods, the proposed M-LRM can generate 3D shapes of high fidelity. Experimental studies demonstrate that our model achieves a significant performance gain and faster training convergence. Project page: urlhttps://murphylmf.github.io/M-LRM/.

Key facts. Cited by 6 papers in the map (data through 7 Oct 2026). Builds on 72 of its 78 references that are in the map. First posted on arXiv 11 Jun 2024.

Builds on

72 of 78 references.

References · 72

  1. 2020Denoising Diffusion Probabilistic Modelscited by 20,851
  2. 2021High-Resolution Image Synthesis with Latent Diffusion Modelscited by 18,694
  3. 2018The Unreasonable Effectiveness of Deep Features as a Perceptual Metriccited by 11,029
  4. 2020Denoising Diffusion Implicit Modelscited by 9,655
  5. 2020Score-Based Generative Modeling through Stochastic Differential Equationscited by 8,964
  6. 2023Segment Anythingcited by 8,158
  7. 20233D Gaussian Splatting for Real-Time Radiance Field Renderingcited by 6,141
  8. 2018A Style-Based Generator Architecture for Generative Adversarial Networkscited by 5,986
  9. 2019Analyzing and Improving the Image Quality of StyleGANcited by 3,580
  10. 2022DreamFusion: Text-to-3D using 2D Diffusioncited by 3,006
  11. 2017Progressive Growing of GANs for Improved Quality, Stability, and Variationcited by 2,967
  12. 2018Large Scale GAN Training for High Fidelity Natural Image Synthesiscited by 2,609
38 more
  1. 2021NeuS: Learning Neural Implicit Surfaces by Volume Rendering for Multi-view Reconstructioncited by 1,701
  2. 2020pixelNeRF: Neural Radiance Fields from One or Few Imagescited by 1,574
  3. 2023DUSt3R: Geometric 3D Vision Made Easycited by 1,526
  4. 2022Objaverse: A Universe of Annotated 3D Objectscited by 1,522
  5. 2023Zero-1-to-3: Zero-shot One Image to 3D Objectcited by 1,483
  6. 2022Magic3D: High-Resolution Text-to-3D Content Creationcited by 1,285
  7. 2023ProlificDreamer: High-Fidelity and Diverse Text-to-3D Generation with Variational Score Distillationcited by 1,207
  8. 2021Efficient Geometry-aware 3D Generative Adversarial Networkscited by 1,204
  9. 2021Alias-Free Generative Adversarial Networkscited by 1,181
  10. 2023MVDream: Multi-view Diffusion for 3D Generationcited by 928
  11. 2023DreamGaussian: Generative Gaussian Splatting for Efficient 3D Content Creationcited by 837
  12. 2023LRM: Large Reconstruction Model for Single Image to 3Dcited by 834
  13. 2020GIRAFFE: Representing Scenes as Compositional Generative Neural Feature Fieldscited by 784
  14. 2023Objaverse-XL: A Universe of 10M+ 3D Objectscited by 767
  15. 2021MVSNeRF: Fast Generalizable Radiance Field Reconstruction from Multi-View Stereocited by 735
  16. 2024LGM: Large Multi-View Gaussian Model for High-Resolution 3D Content Creationcited by 730
  17. 2021IBRNet: Learning Multi-View Image-Based Renderingcited by 698
  18. 2022Point-E: A System for Generating 3D Point Clouds from Complex Promptscited by 694
  19. 2023Fantasia3D: Disentangling Geometry and Appearance for High-quality Text-to-3D Content Creationcited by 684
  20. 2023Wonder3D: Single Image to 3D using Cross-Domain Diffusioncited by 682
  21. 2023SyncDreamer: Generating Multiview-consistent Images from a Single-view Imagecited by 638
  22. 2022Google Scanned Objects: A High-Quality Dataset of 3D Scanned Household Itemscited by 601
  23. 2022Score Jacobian Chaining: Lifting Pretrained 2D Diffusion Models for 3D Generationcited by 597
  24. 2017Generative Adversarial Networks: An Overviewcited by 588
  25. 2023One-2-3-45: Any Single Image to 3D Mesh in 45 Seconds without Per-Shape Optimizationcited by 555
  26. 2023Zero123++: a Single Image to Consistent Multi-view Diffusion Base Modelcited by 516
  27. 2023Scaling up GANs for Text-to-Image Synthesiscited by 492
  28. 2021StyleNeRF: A Style-based 3D-Aware Generator for High-resolution Image Synthesiscited by 477
  29. 2021Putting NeRF on a Diet: Semantically Consistent Few-Shot View Synthesiscited by 464
  30. 2024InstantMesh: Efficient 3D Mesh Generation from a Single Image with Sparse-view Large Reconstruction Modelscited by 421
  31. 2023Shap-E: Generating Conditional 3D Implicit Functionscited by 379
  32. 2023Instant3D: Fast Text-to-3D with Sparse-View Generation and Large Reconstruction Modelcited by 376
  33. 2024GRM: Large Gaussian Reconstruction Model for Efficient 3D Reconstruction and Generationcited by 298
  34. 2023LucidDreamer: Towards High-Fidelity Text-to-3D Generation via Interval Score Matchingcited by 290
  35. 20223D Neural Field Generation using Triplane Diffusioncited by 274
  36. 2023Triplane Meets Gaussian Splatting: Fast and Generalizable Single-View 3D Reconstruction with Transformerscited by 257
  37. 2023ImageDream: Image-Prompt Multi-view Diffusion for 3D Generationcited by 256
  38. 2023LucidDreamer: Domain-free Generation of 3D Gaussian Splatting Scenescited by 228

50 most cited of 72 All 72 (JSON)

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2024: 3; 2025: 2; 2026: 1.

6 papers.

  1. 2024EdgeRunner: Auto-regressive Auto-encoder for Artistic Mesh Generationcited by 84
  2. 2025MaterialMVP: Illumination-Invariant Material Generation via Multi-view PBR Diffusioncited by 28
  3. 2024ScaleDreamer: Scalable Text-to-3D Synthesis with Asynchronous Score Distillationcited by 27
  4. 2024Dust to Tower: Coarse-to-Fine Photo-Realistic Scene Reconstruction from Sparse Uncalibrated Imagescited by 8
  5. 2025SuperCarver: Texture-Consistent 3D Geometry Super-Resolution for High-Fidelity Surface Detail Generationcited by 2
  6. 2026Fus3D: Decoding Consolidated 3D Geometry from Feed-forward Geometry Transformer Latentscited by 0