mlsanityData to 7 Oct 2026

Learning to Reconstruct Shapes from Unseen Classes

arXiv 1812.11166 ↗First posted 28 Dec 2018cs.CV cs.AIcited by 60

Not on the map. Why?

Abstract (arXiv)

From a single image, humans are able to perceive the full 3D shape of an object by exploiting learned shape priors from everyday life. Contemporary single-image 3D reconstruction algorithms aim to solve this task in a similar fashion, but often end up with priors that are highly biased by training classes. Here we present an algorithm, Generalizable Reconstruction (GenRe), designed to capture more generic, class-agnostic shape priors. We achieve this with an inference network and training procedure that combine 2.5D representations of visible surfaces (depth and silhouette), spherical shape representations of both visible and non-visible surfaces, and 3D voxel-based representations, in a principled manner that exploits the causal structure of how 3D shapes give rise to 2D images. Experiments demonstrate that GenRe performs well on single-view shape reconstruction, and generalizes to diverse novel objects from categories not seen during training.

Key facts. Cited by 60 papers in the map (data through 7 Oct 2026). First posted on arXiv 28 Dec 2018.

Builds on

No reference list yet.

Built on by

Cited by year

Citing papers per year: 2021: 14; 2022: 16; 2023: 12; 2024: 12; 2025: 6.

60 papers.

Sort:

By area:

  1. 20213D Shape Generation and Completion through Point-Voxel Diffusioncited by 516
  2. 2021Zero-Shot Text-Guided Object Generation with Dream Fieldscited by 513
  3. 2021ABO: Dataset and Benchmarks for Real-World 3D Object Understandingcited by 360
  4. 2024TripoSR: Fast 3D Object Reconstruction from a Single Imagecited by 227
  5. 2022CHORE: Contact, Human and Object REconstruction from a single RGB imagecited by 95
  6. 2022Fast Point Cloud Generation with Straight Flowscited by 56
  7. 2024Human-3Diffusion: Realistic Avatar Creation via Explicit 3D Consistent Diffusion Modelscited by 44
  8. 2022Autoregressive 3D Shape Generation via Canonical Mappingcited by 37
  9. 2023Template Free Reconstruction of Human-object Interaction with Procedural Interaction Generationcited by 37
  10. 2022ConDor: Self-Supervised Canonicalization of 3D Pose for Partial Shapescited by 31
  11. 2022GenSDF: Two-Stage Learning of Generalizable Signed Distance Functionscited by 30
  12. 2023ZeroShape: Regression-based Zero-shot Shape Reconstructioncited by 30
38 more
  1. 2023HarmonyView: Harmonizing Consistency and Diversity in One-Image-to-3Dcited by 27
  2. 2022SurfGen: Adversarial 3D Shape Synthesis with Explicit Surface Discriminatorscited by 26
  3. 2022PatchComplete: Learning Multi-Resolution Patch Priors for 3D Shape Completion on Unseen Categoriescited by 21
  4. 2025Not-So-Optimal Transport Flows for 3D Point Cloud Generationcited by 17
  5. 2021Fully Understanding Generic Objects: Modeling, Segmentation, and Reconstructioncited by 16
  6. 2022Your Out-of-Distribution Detection Method is Not Robust!cited by 16
  7. 2024Gen-3Diffusion: Realistic Image-to-3D Generation via 2D & 3D Diffusion Synergycited by 16
  8. 2021StrobeNet: Category-Level Multiview Reconstruction of Articulated Objectscited by 14
  9. 2022Semi-Supervised Single-View 3D Reconstruction via Prototype Shape Priorscited by 14
  10. 2023Iterative Superquadric Recomposition of 3D Objects from Multiple Viewscited by 13
  11. 2021DeepCurrents: Learning Implicit Representations of Shapes with Boundariescited by 12
  12. 2021A Geometry-Informed Deep Learning Framework for Ultra-Sparse 3D Tomographic Image Reconstructioncited by 11
  13. 2022Neural Vector Fields for Implicit Surface Representation and Inferencecited by 10
  14. 2022Single-view 3D Mesh Reconstruction for Seen and Unseen Categoriescited by 10
  15. 2023CCD-3DR: Consistent Conditioning in Diffusion for Single-Image 3D Reconstructioncited by 10
  16. 2023MVDD: Multi-View Depth Diffusion Modelscited by 10
  17. 2024RHOBIN Challenge: Reconstruction of Human Object Interactioncited by 10
  18. 2021Fostering Generalization in Single-view 3D Reconstruction by Learning a Hierarchy of Local and Global Shape Priorscited by 9
  19. 2022Planes vs. Chairs: Category-guided 3D shape learning without any 3D cuescited by 9
  20. 2023SENS: Part-Aware Sketch-based Implicit Neural Shape Modelingcited by 8
  21. 2023NAISR: A 3D Neural Additive Model for Interpretable Shape Representationcited by 7
  22. 2024Robust 3D Shape Reconstruction in Zero-Shot from a Single Image in the Wildcited by 7
  23. 2022Neural Shape Compiler: A Unified Framework for Transforming between Text, Point Cloud, and Programcited by 6
  24. 2024The More You See in 2D, the More You Perceive in 3Dcited by 5
  25. 2025SPGen: Spherical Projection as Consistent and Flexible Representation for Single Image 3D Shape Generationcited by 5
  26. 2021SIMstack: A Generative Shape and Instance Model for Unordered Object Stackscited by 4
  27. 2021Monocular Depth Estimation for Soft Visuotactile Sensorscited by 3
  28. 2021Towards Panoptic 3D Parsing for Single Image in the Wildcited by 3
  29. 2023A Review of Deep Learning-Powered Mesh Reconstruction Methodscited by 3
  30. 2024Learning Local Pattern Modularization for Point Cloud Reconstruction from Unseen Classescited by 3
  31. 2021The Surprising Positive Knowledge Transfer in Continual 3D Object Shape Reconstructioncited by 2
  32. 2022Improved α-GAN architecture for generating 3D connected volumes with an application to radiosurgery treatment planningcited by 2
  33. 2024Point Cloud Synthesis Using Inner Product Transformscited by 2
  34. 2021DDR-Net: Learning Multi-Stage Multi-View Stereo With Dynamic Depth Rangecited by 1
  35. 2022SingleSketch2Mesh : Generating 3D Mesh model from Sketchcited by 1
  36. 2023Single-view 3D reconstruction via inverse procedural modelingcited by 1
  37. 2024MeTTA: Single-View to 3D Textured Mesh Reconstruction with Test-Time Adaptationcited by 1
  38. 2025PCF-Grasp: Converting Point Completion to Geometry Feature to Enhance 6-DoF Graspcited by 1

50 most cited of 60 All 60 (JSON)