mlsanityData to 14 Oct 2026

FvOR: Robust Joint Shape and Pose Optimization for Few-view Object Reconstruction

arXiv 2205.07763 ↗First posted 16 May 2022cs.CVcited by 19

Not on the map. Why?

Abstract (arXiv)

Reconstructing an accurate 3D object model from a few image observations remains a challenging problem in computer vision. State-of-the-art approaches typically assume accurate camera poses as input, which could be difficult to obtain in realistic settings. In this paper, we present FvOR, a learning-based object reconstruction method that predicts accurate 3D models given a few images with noisy input poses. The core of our approach is a fast and robust multi-view reconstruction algorithm to jointly refine 3D geometry and camera pose estimation using learnable neural network modules. We provide a thorough benchmark of state-of-the-art approaches for this problem on ShapeNet. Our approach achieves best-in-class results. It is also two orders of magnitude faster than the recent optimization-based approach IDR. Our code is released at urlhttps://github.com/zhenpeiyang/FvOR/

Key facts. Cited by 19 papers in the map (data through 14 Oct 2026). Builds on 46 of its 73 references that are in the map. First posted on arXiv 16 May 2022.

Builds on

46 of 73 references.

References · 46

  1. 2015Deep Residual Learning for Image Recognitioncited by 52,096
  2. 2014Adam: A Method for Stochastic Optimizationcited by 37,240
  3. 2015ShapeNet: An Information-Rich 3D Model Repositorycited by 2,897
  4. 2019DeepSDF: Learning Continuous Signed Distance Functions for Shape Representationcited by 2,689
  5. 2018Occupancy Networks: Learning 3D Reconstruction in Function Spacecited by 2,041
  6. 2020Transformers are RNNs: Fast Autoregressive Transformers with Linear Attentioncited by 2,022
  7. 2021NeuS: Learning Neural Implicit Surfaces by Volume Rendering for Multi-view Reconstructioncited by 1,712
  8. 2020pixelNeRF: Neural Radiance Fields from One or Few Imagescited by 1,584
  9. 20163D U-Net: Learning Dense Volumetric Segmentation from Sparse Annotationcited by 1,476
  10. 2014Depth Map Prediction from a Single Image using a Multi-Scale Deep Networkcited by 1,274
  11. 2018Learning Implicit Fields for Generative Shape Modelingcited by 1,060
  12. 2021LoFTR: Detector-Free Local Feature Matching with Transformerscited by 984
34 more
  1. 2016A Point Set Generation Network for 3D Object Reconstruction from a Single Imagecited by 979
  2. 2016Unsupervised Monocular Depth Estimation with Left-Right Consistencycited by 820
  3. 2019PIFu: Pixel-Aligned Implicit Function for High-Resolution Clothed Human Digitizationcited by 818
  4. 2017PoseCNN: A Convolutional Neural Network for 6D Object Pose Estimation in Cluttered Scenescited by 775
  5. 2018Pixel2Mesh: Generating 3D Mesh Models from Single RGB Imagescited by 651
  6. 2021UNISURF: Unifying Neural Implicit Surfaces and Radiance Fields for Multi-View Reconstructioncited by 646
  7. 2021BARF: Bundle-Adjusting Neural Radiance Fieldscited by 642
  8. 2020Neural Body: Implicit Neural Representations with Structured Latent Codes for Novel View Synthesis of Dynamic Humanscited by 634
  9. 20163D-R2N2: A Unified Approach for Single and Multi-view 3D Object Reconstructioncited by 588
  10. 2018AtlasNet: A Papier-Mach'e Approach to Learning 3D Surface Generationcited by 539
  11. 2019Normalized Object Coordinate Space for Category-Level 6D Object Pose and Size Estimationcited by 495
  12. 2014Predicting Depth, Surface Normals and Semantic Labels with a Common Multi-Scale Convolutional Architecturecited by 483
  13. 2019DISN: Deep Implicit Surface Network for High-quality Single-view 3D Reconstructioncited by 333
  14. 2019What Do Single-view 3D Reconstruction Networks Learn?cited by 260
  15. 2017Learning a Multi-View Stereo Machinecited by 194
  16. 2018DeepV2D: Video to Depth with Differentiable Structure from Motioncited by 185
  17. 2016Learning a Predictable and Generative Vector Representation for Objectscited by 173
  18. 2019SDFDiff: Differentiable Rendering of Signed Distance Fields for 3D Shape Optimizationcited by 159
  19. 2021Neural Human Performer: Learning Generalizable Radiance Fields for Human Performance Renderingcited by 158
  20. 2021GNeRF: GAN-based Neural Radiance Field without Posed Cameracited by 153
  21. 2018CodeSLAM - Learning a Compact, Optimisable Representation for Dense Visual SLAMcited by 152
  22. 2021NeRS: Neural Reflectance Surfaces for Sparse-view 3D Reconstruction in the Wildcited by 136
  23. 2017MarrNet: 3D Shape Reconstruction via 2.5D Sketchescited by 108
  24. 2020Pix2Vox++: Multi-scale Context-aware 3D Object Reconstruction from Single and Multiple Imagescited by 79
  25. 2021Unsupervised Learning of 3D Object Categories from Videos in the Wildcited by 67
  26. 2014Viewpoints and Keypointscited by 59
  27. 2014Category-Specific Object Reconstruction from a Single Imagecited by 56
  28. 2021Extreme Rotation Estimation using Dense Correlation Volumescited by 42
  29. 2021PVA: Pixel-aligned Volumetric Avatarscited by 40
  30. 2021Deep Learning on Monocular Object Pose Detection and Tracking: A Comprehensive Overviewcited by 31
  31. 2019Photometric Mesh Optimization for Video-Aligned 3D Object Reconstructioncited by 28
  32. 2020Deep Optimized Priors for 3D Shape Modeling and Reconstructioncited by 20
  33. 2016Single Image 3D Interpreter Networkcited by 19
  34. 2020On the generalization of learning-based 3D reconstructioncited by 12

Built on by

Cited by year

Citing papers per year: 2022: 3; 2023: 6; 2024: 7; 2025: 3.

19 papers.

Sort:

By area:

  1. 2023PF-LRM: Pose-Free Large Reconstruction Model for Joint Pose and Shape Predictioncited by 165
  2. 2023BundleSDF: Neural 6-DoF Tracking and 3D Reconstruction of Unknown Objectscited by 148
  3. 2024MVDiffusion++: A Dense High-resolution Multi-view Diffusion Model for Single or Sparse-view 3D Object Reconstructioncited by 95
  4. 2022Few-View Object Reconstruction with Unknown Categories and Camera Posescited by 53
  5. 2023ViP-NeRF: Visibility Prior for Sparse Input Neural Radiance Fieldscited by 43
  6. 2024SpaRP: Fast 3D Object Reconstruction and Pose Estimation from Sparse Viewscited by 35
  7. 2024MVDiff: Scalable and Flexible Multi-View Diffusion for 3D Object Reconstruction from Single-Viewcited by 6
  8. 2024Extreme Rotation Estimation in the Wildcited by 6
  9. 2025Emergent Extreme-View Geometry in 3D Foundation Modelscited by 6
  10. 2023Long-Range Grouping Transformer for Multi-View 3D Reconstructioncited by 5
  11. 2023LASA: Instance Reconstruction from Real Scans using A Large-scale Aligned Shape Annotation Datasetcited by 5
  12. 2024DPA-Net: Structured 3D Abstraction from Sparse Views via Differentiable Primitive Assemblycited by 5
7 more
  1. 2022HM3D-ABO: A Photo-realistic Dataset for Object-centric Multi-view 3D Reconstructioncited by 4
  2. 2024Exploiting Priors from 3D Diffusion Models for RGB-Based One-Shot View Planningcited by 4
  3. 2022Equivariant Light Field Convolution and Transformercited by 2
  4. 2025OnlineSplatter: Pose-Free Online 3D Reconstruction for Free-Moving Objectscited by 2
  5. 2023SnakeVoxFormer: Transformer-based Single ImageVoxel Reconstruction with Run Length Encodingcited by 0
  6. 2024Shape2.5D: A Dataset of Texture-less Surfaces for Depth and Normals Estimationcited by 0
  7. 2025Pl"uckeRF: A Line-based 3D Representation for Few-view Reconstructioncited by 0