mlsanityData to 7 Oct 2026

Pixel2Mesh++: Multi-View 3D Mesh Generation via Deformation

arXiv 1908.01491 ↗First posted 5 Aug 2019cs.CVcited by 103

Not on the map. Why?

Abstract (arXiv)

We study the problem of shape generation in 3D mesh representation from a few color images with known camera poses. While many previous works learn to hallucinate the shape directly from priors, we resort to further improving the shape quality by leveraging cross-view information with a graph convolutional network. Instead of building a direct mapping function from images to 3D shape, our model learns to predict series of deformations to improve a coarse shape iteratively. Inspired by traditional multiple view geometry methods, our network samples nearby area around the initial mesh's vertex locations and reasons an optimal deformation using perceptual feature statistics built from multiple input images. Extensive experiments show that our model produces accurate 3D shape that are not only visually plausible from the input perspectives, but also well aligned to arbitrary viewpoints. With the help of physically driven architecture, our model also exhibits generalization capability across different semantic categories, number of input images, and quality of mesh initialization.

Key facts. Cited by 103 papers in the map (data through 7 Oct 2026). First posted on arXiv 5 Aug 2019.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 23; 2022: 28; 2023: 25; 2024: 8; 2025: 12; 2026: 7.

103 papers.

Sort:

By area:

  1. 2021NeuS: Learning Neural Implicit Surfaces by Volume Rendering for Multi-view Reconstructioncited by 1,701
  2. 2023One-2-3-45: Any Single Image to 3D Mesh in 45 Seconds without Per-Shape Optimizationcited by 555
  3. 2023DreamBooth3D: Subject-Driven Text-to-3D Generationcited by 235
  4. 2025SAM 3D: 3Dfy Anything in Imagescited by 230
  5. 2024Gaussian in the Wild: 3D Gaussian Splatting for Unconstrained Image Collectionscited by 117
  6. 2022POCO: Point Convolution for Surface Reconstructioncited by 91
  7. 2023HumanGaussian: Text-Driven 3D Human Generation with Gaussian Splattingcited by 89
  8. 2023Multiview Compressive Coding for 3D Reconstructioncited by 71
  9. 2022A Survey on Graph Neural Networks and Graph Transformers in Computer Vision: A Task-Oriented Perspectivecited by 56
  10. 2021CSG-Stump: A Learning Friendly CSG-Like Representation for Interpretable Shape Parsingcited by 51
  11. 2021A Deep-Learning Approach For Direct Whole-Heart Mesh Reconstructioncited by 47
  12. 20223D Shape Reconstruction from 2D Images with Disentangled Attribute Flowcited by 45
38 more
  1. 2022Multi-View Mesh Reconstruction with Neural Deferred Shadingcited by 44
  2. 2021Joint Learning of 3D Shape Retrieval and Deformationcited by 41
  3. 2023Controllable Mesh Generation Through Sparse Latent Point Diffusion Modelscited by 40
  4. 2021Patch2CAD: Patchwise Embedding Learning for In-the-Wild Shape Retrieval from a Single Imagecited by 39
  5. 2023Points-to-3D: Bridging the Gap between Sparse Points and Shape-Controllable Text-to-3D Generationcited by 39
  6. 2021SAIL-VOS 3D: A Synthetic Dataset and Baselines for Object Detection and 3D Mesh Reconstruction from Video Datacited by 38
  7. 20243DRealCar: An In-the-wild RGB-D Car Dataset with 360-degree Viewscited by 37
  8. 2023NeAT: Learning Neural Implicit Surfaces with Arbitrary Topologies from Multi-view Imagescited by 32
  9. 2023ZeroShape: Regression-based Zero-shot Shape Reconstructioncited by 30
  10. 2022Vox2Cortex: Fast Explicit Reconstruction of Cortical Surfaces from 3D MRI Scans with Geometric Deep Neural Networkscited by 27
  11. 20213D Adversarial Attacks Beyond Point Cloudcited by 26
  12. 2021OctField: Hierarchical Implicit Functions for 3D Modelingcited by 25
  13. 2024Reconstructing Hand-Held Objects in 3D from Images and Videoscited by 23
  14. 2021Learning Compositional Representation for 4D Captures with Neural ODEcited by 22
  15. 2022CSDN: Cross-modal Shape-transfer Dual-refinement Network for Point Cloud Completioncited by 22
  16. 2022Pixel2Mesh++: 3D Mesh Generation and Refinement from Multi-View Imagescited by 21
  17. 2021Voxel-based 3D Detection and Reconstruction of Multiple Objects from a Single Imagecited by 20
  18. 2021Fully Understanding Generic Objects: Modeling, Segmentation, and Reconstructioncited by 16
  19. 2022Reinforcement learning for automatic quadrilateral mesh generation: a soft actor-critic approachcited by 16
  20. 2023ShapeClipper: Scalable 3D Shape Learning from Single-View Images via Geometric and CLIP-based Consistencycited by 16
  21. 2022H4D: Human 4D Modeling by Learning Neural Compositional Representationcited by 15
  22. 20233DAxiesPrompts: Unleashing the 3D Spatial Task Capabilities of GPT-4Vcited by 15
  23. 2021Deep Hybrid Self-Prior for Full 3D Mesh Generationcited by 13
  24. 2022Structural Causal 3D Reconstructioncited by 12
  25. 2025ARMesh: Autoregressive Mesh Generation via Next-Level-of-Detail Predictioncited by 11
  26. 2023CCD-3DR: Consistent Conditioning in Diffusion for Single-Image 3D Reconstructioncited by 10
  27. 2025Micro-macro Wavelet-based Gaussian Splatting for 3D Reconstruction from Unconstrained Imagescited by 10
  28. 2021Revisiting Point Cloud Simplification: A Learnable Feature Preserving Approachcited by 9
  29. 2022A Real World Dataset for Multi-view 3D Reconstructioncited by 9
  30. 2022Few-shot Single-view 3D Reconstruction with Memory Prior Contrastive Networkcited by 9
  31. 2022What's the Situation with Intelligent Mesh Generation: A Survey and Perspectivescited by 9
  32. 2021Shape Controllable Virtual Try-on for Underwear Modelscited by 8
  33. 2021DenseGAP: Graph-Structured Dense Correspondence Learning with Anchor Pointscited by 8
  34. 2022LoRD: Local 4D Implicit Representation for High-Fidelity Dynamic Human Modelingcited by 8
  35. 2022GARNet: Global-Aware Multi-View 3D Reconstruction Network and the Cost-Performance Tradeoffcited by 8
  36. 2023Decoupled Iterative Refinement Framework for Interacting Hands Reconstruction from a Single RGB Imagecited by 8
  37. 2023Few-Shot Physically-Aware Articulated Mesh Generation via Hierarchical Deformationcited by 8
  38. 2021Learning Canonical 3D Object Representation for Fine-Grained Recognitioncited by 7

50 most cited of 103 All 103 (JSON)