mlsanityData to 14 Oct 2026

CUPID: Generative 3D Reconstruction via Joint Object and Pose Modeling

arXiv 2510.20776 ↗First posted 23 Oct 2025cs.CVcited by 8

Not on the map. Why?

Abstract (arXiv)

We introduce Cupid, a generative 3D reconstruction framework that jointly models the full distribution over both canonical objects and camera poses. Our two-stage flow-based model first generates a coarse 3D structure and 2D-3D correspondences to estimate the camera pose robustly. Conditioned on this pose, a refinement stage injects pixel-aligned image features directly into the generative process, marrying the rich prior of a generative model with the geometric fidelity of reconstruction. This strategy achieves exceptional faithfulness, outperforming state-of-the-art reconstruction methods by over 3 dB PSNR and 10% in Chamfer Distance. As a unified generative model that decouples the object and camera pose, Cupid naturally extends to multi-view and scene-level reconstruction tasks without requiring post-hoc optimization or fine-tuning.

Key facts. Cited by 8 papers in the map (data through 14 Oct 2026). Builds on 61 of its 71 references that are in the map. First posted on arXiv 23 Oct 2025.

Builds on

61 of 71 references.

References · 61

  1. 2021Learning Transferable Visual Models From Natural Language Supervisioncited by 33,744
  2. 2021High-Resolution Image Synthesis with Latent Diffusion Modelscited by 18,863
  3. 2022Photorealistic Text-to-Image Diffusion Models with Deep Language Understandingcited by 6,355
  4. 20233D Gaussian Splatting for Real-Time Radiance Field Renderingcited by 6,226
  5. 2022Classifier-Free Diffusion Guidancecited by 5,847
  6. 2022Flow Matching for Generative Modelingcited by 5,702
  7. 2022DreamFusion: Text-to-3D using 2D Diffusioncited by 3,025
  8. 2024SAM 2: Segment Anything in Images and Videoscited by 2,863
  9. 2023DUSt3R: Geometric 3D Vision Made Easycited by 1,567
  10. 2025VGGT: Visual Geometry Grounded Transformercited by 1,539
  11. 2023Zero-1-to-3: Zero-shot One Image to 3D Objectcited by 1,489
  12. 2024Depth Anything V2cited by 1,422
38 more
  1. 2023LRM: Large Reconstruction Model for Single Image to 3Dcited by 849
  2. 2023Objaverse-XL: A Universe of 10M+ 3D Objectscited by 774
  3. 2024Structured 3D Latents for Scalable and Versatile 3D Generationcited by 770
  4. 2024LGM: Large Multi-View Gaussian Model for High-Resolution 3D Content Creationcited by 739
  5. 2023SyncDreamer: Generating Multiview-consistent Images from a Single-view Imagecited by 645
  6. 2022Google Scanned Objects: A High-Quality Dataset of 3D Scanned Household Itemscited by 612
  7. 2023One-2-3-45: Any Single Image to 3D Mesh in 45 Seconds without Per-Shape Optimizationcited by 560
  8. 2025Continuous 3D Perception Model with Persistent Statecited by 548
  9. 2023MultiDiffusion: Fusing Diffusion Paths for Controlled Image Generationcited by 536
  10. 2023Zero123++: a Single Image to Consistent Multi-view Diffusion Base Modelcited by 521
  11. 2024CLAY: A Controllable Large-scale Generative Model for Creating High-quality 3D Assetscited by 455
  12. 2024InstantMesh: Efficient 3D Mesh Generation from a Single Image with Sparse-view Large Reconstruction Modelscited by 433
  13. 2024CAT3D: Create Anything in 3D with Multi-View Diffusion Modelscited by 432
  14. 2023FoundationPose: Unified 6D Pose Estimation and Tracking of Novel Objectscited by 429
  15. 2023Instant3D: Fast Text-to-3D with Sparse-View Generation and Large Reconstruction Modelcited by 378
  16. 2025Fast3R: Towards 3D Reconstruction of 1000+ Images in One Forward Passcited by 367
  17. 2021ABO: Dataset and Benchmarks for Real-World 3D Object Understandingcited by 366
  18. 2025Hunyuan3D 2.0: Scaling Diffusion Models for High Resolution Textured 3D Assets Generationcited by 356
  19. 2025GEN3C: 3D-Informed World-Consistent Video Generation with Precise Camera Controlcited by 341
  20. 2023ReconFusion: 3D Reconstruction with Diffusion Priorscited by 318
  21. 20203D-FUTURE: 3D Furniture shape with TextUREcited by 311
  22. 2024GRM: Large Gaussian Reconstruction Model for Efficient 3D Reconstruction and Generationcited by 301
  23. 2022Novel View Synthesis with Diffusion Modelscited by 300
  24. 2024MoGe: Unlocking Accurate Monocular Geometry Estimation for Open-Domain Images with Optimal Training Supervisioncited by 299
  25. 2024TripoSR: Fast 3D Object Reconstruction from a Single Imagecited by 232
  26. 2024LVSM: A Large View Synthesis Model with Minimal 3D Inductive Biascited by 189
  27. 2025Stable Virtual Camera: Generative View Synthesis with Diffusion Modelscited by 182
  28. 2025FLARE: Feed-forward Geometry, Appearance and Camera Estimation from Uncalibrated Sparse Viewscited by 180
  29. 2023Habitat Synthetic Scenes Dataset (HSSD-200): An Analysis of 3D Scene Scale and Realism Tradeoffs for ObjectGoal Navigationcited by 167
  30. 2023PF-LRM: Pose-Free Large Reconstruction Model for Joint Pose and Shape Predictioncited by 165
  31. 2025MUSt3R: Multi-view Network for Stereo 3D Reconstructioncited by 141
  32. 2023Flexible Isosurface Extraction for Gradient-Based Mesh Optimizationcited by 139
  33. 2024MeshLRM: Large Reconstruction Model for High-Quality Meshescited by 139
  34. 2024Cameras as Rays: Pose Estimation via Ray Diffusioncited by 131
  35. 2021Using Shape to Categorize: Low-Shot Learning with an Explicit Shape Biascited by 118
  36. 2024MIDI: Multi-Instance Diffusion for Single Image to 3D Scene Generationcited by 117
  37. 2025CAST: Component-Aligned 3D Scene Reconstruction from an RGB Imagecited by 106
  38. 2024SLAM3R: Real-Time Dense Scene Reconstruction from Monocular RGB Videoscited by 102

50 most cited of 61 All 61 (JSON)

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2026: 8.

8 papers.

  1. 2026Picasso: Holistic Scene Reconstruction with Physics-Constrained Samplingcited by 4
  2. 2026AniGen: Unified S3 Fields for Animatable 3D Asset Generationcited by 3
  3. 2026Pose-Aware Diffusion for 3D Generationcited by 1
  4. 2026FlowObject: Flow Steering for Bridging Generative Priors and Reconstruction Fidelitycited by 1
  5. 2026ReconPlusGen: Injecting Reconstruction Prior into Multi-view 3D Generation through Noise Inversion and Modulationcited by 1
  6. 2026MORPHOS: Autoregressive 4D Generation with Temporal Structured Latentscited by 0
  7. 2026Mira-Scene: Pixel-Aligned Layouts for Generative 3D Scene Reconstructioncited by 0
  8. 2026SPOON: Towards Coherent Compositional 3D Scene Generation from Uncalibrated Multi-view Imagescited by 0