mlsanityData to 14 Oct 2026

ReconPlusGen: Injecting Reconstruction Prior into Multi-view 3D Generation through Noise Inversion and Modulation

arXiv 2609.11129 ↗First posted 10 Sep 2026cs.CVcited by 1

Not on the map. Why?

Abstract (arXiv)

Qualitative results and an illustration of our core idea. Top left: reconstruction results on benchmark images. Top right: reconstruction results on real-world images. Bottom: illustration of reconstruction-guided noise initialization and modulation. Given multiple input images, we predict a point cloud in canonical space, deterministically inject the predicted geometry into the diffusion process through noise inversion, and modulate the resulting noise to preserve the generative flexibility required to complete unobserved regions and refine visible geometry.

Key facts. Cited by 1 paper in the map (data through 14 Oct 2026). Builds on 56 of its 62 references that are in the map. First posted on arXiv 10 Sep 2026.

Builds on

56 of 62 references.

References · 56

  1. 2021NeuS: Learning Neural Implicit Surfaces by Volume Rendering for Multi-view Reconstructioncited by 1,712
  2. 2023DUSt3R: Geometric 3D Vision Made Easycited by 1,567
  3. 2025VGGT: Visual Geometry Grounded Transformercited by 1,539
  4. 2022Null-text Inversion for Editing Real Images using Guided Diffusion Modelscited by 1,179
  5. 2023LRM: Large Reconstruction Model for Single Image to 3Dcited by 849
  6. 2024Structured 3D Latents for Scalable and Versatile 3D Generationcited by 770
  7. 2024LGM: Large Multi-View Gaussian Model for High-Resolution 3D Content Creationcited by 739
  8. 2025Depth Anything 3: Recovering the Visual Space from Any Viewscited by 692
  9. 20233DShape2VecSet: A 3D Shape Representation for Neural Fields and Generative Diffusion Modelscited by 458
  10. 2024CLAY: A Controllable Large-scale Generative Model for Creating High-quality 3D Assetscited by 455
  11. 2024InstantMesh: Efficient 3D Mesh Generation from a Single Image with Sparse-view Large Reconstruction Modelscited by 433
  12. 2023Instant3D: Fast Text-to-3D with Sparse-View Generation and Large Reconstruction Modelcited by 378
38 more
  1. 2025Fast3R: Towards 3D Reconstruction of 1000+ Images in One Forward Passcited by 367
  2. 2023OmniObject3D: Large-Vocabulary 3D Object Dataset for Realistic Perception, Reconstruction and Generationcited by 326
  3. 2025π3: Permutation-Equivariant Visual Geometry Learningcited by 319
  4. 2022EDICT: Exact Diffusion Inversion via Coupled Transformationscited by 258
  5. 2024Global Structure-from-Motion Revisitedcited by 218
  6. 2023DMV3D: Denoising Multi-View Diffusion using 3D Large Reconstruction Modelcited by 214
  7. 2025Hunyuan3D 2.1: From Images to High-Fidelity 3D Assets with Production-Ready PBR Materialcited by 165
  8. 2024MASt3R-SfM: a Fully-Integrated Solution for Unconstrained Structure-from-Motioncited by 162
  9. 2024MeshLRM: Large Reconstruction Model for High-Quality Meshescited by 139
  10. 2025VGGT-SLAM: Dense RGB SLAM Optimized on the SL(4) Manifoldcited by 136
  11. 2024ReNoise: Real Image Inversion Through Iterative Noisingcited by 128
  12. 2024InitNO: Boosting Text-to-Image Diffusion Models via Initial Noise Optimizationcited by 123
  13. 2024CraftsMan3D: High-fidelity Mesh Generation with 3D Native Generation and Interactive Geometry Refinercited by 123
  14. 2024D-Flow: Differentiating through Flows for Controlled Generationcited by 122
  15. 2024ReNO: Enhancing One-step Text-to-Image Models through Reward-based Noise Optimizationcited by 119
  16. 2025VGGT-Long: Chunk it, Loop it, Align it -- Pushing VGGT's Limits on Kilometer-scale Long RGB Sequencescited by 115
  17. 2024RaDe-GS: Rasterizing Depth in Gaussian Splattingcited by 111
  18. 2023HiFA: High-fidelity Text-to-3D Generation with Advanced Diffusion Guidancecited by 110
  19. 2023End-to-End Diffusion Latent Optimization Improves Classifier Guidancecited by 108
  20. 2024Dora: Sampling and Benchmarking for 3D Shape Variational Auto-Encoderscited by 98
  21. 2024Golden Noise for Diffusion Models: A Learning Frameworkcited by 92
  22. 2025Sparc3D: Sparse Representation and Construction for High-Resolution 3D Shapes Modelingcited by 89
  23. 2021PriorGrad: Improving Conditional Denoising Diffusion Models with Data-Dependent Adaptive Priorcited by 80
  24. 2024Scaling Mesh Generation via Compressive Tokenizationcited by 73
  25. 2025DeepMesh: Auto-Regressive Artist-mesh Creation with Reinforcement Learningcited by 65
  26. 2024A Noise is Worth Diffusion Guidancecited by 49
  27. 2021PaddleSeg: A High-Efficient Development Toolkit for Image Segmentationcited by 35
  28. 2025Noise Hypernetworks: Amortizing Test-Time Compute in Diffusion Modelscited by 35
  29. 2025ReconViaGen: Towards Accurate Multi-view 3D Object Reconstruction via Generationcited by 33
  30. 2024SwiftEdit: Lightning Fast Text-Guided Image Editing via One-Step Diffusioncited by 28
  31. 2026VGGT-Omegacited by 26
  32. 2024MAtCha Gaussians: Atlas of Charts for High-Quality Geometry and Photorealism From Sparse Viewscited by 21
  33. 2025SAIL-Recon: Large SfM by Augmenting Scene Regression with Localizationcited by 20
  34. 2026MV-SAM3D: Adaptive Multi-View Fusion for Layout-Aware 3D Generationcited by 19
  35. 2026Pixal3D: Pixel-Aligned 3D Generation from Imagescited by 14
  36. 2024Eta Inversion: Designing an Optimal Eta Function for Diffusion-based Real Image Editingcited by 12
  37. 2024DetailGen3D: Generative 3D Geometry Enhancement via Data-Dependent Flowcited by 11
  38. 2024Dual-Schedule Inversion: Training- and Tuning-Free Inversion for Real Image Editingcited by 8

50 most cited of 56 All 56 (JSON)

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2026: 1.

1 paper.

  1. 2026UniForge3D: Joint 3D Reconstruction and Generation in a Shared Anchor-Guided Spacecited by 0