# Shelf-Supervised Mesh Prediction in the Wild

arXiv: https://arxiv.org/abs/2102.06195 · HTML: https://mlsanity.com/paper/2102.06195/

## Key facts

- Cited by 65 papers in the map (data through 14 Oct 2026).
- Builds on 43 of its 57 references that are in the map.
- First posted on arXiv 11 Feb 2021.

## Builds on (most cited first, 30 of 43)

- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [Microsoft COCO: Common Objects in Context](https://mlsanity.com/paper/1405.0312/) (2014)
- [The Unreasonable Effectiveness of Deep Features as a Perceptual Metric](https://mlsanity.com/paper/1801.03924/) (2018)
- [A Style-Based Generator Architecture for Generative Adversarial Networks](https://mlsanity.com/paper/1812.04948/) (2018)
- [DeepLab: Semantic Image Segmentation with Deep Convolutional Nets, Atrous Convolution, and Fully Connected CRFs](https://mlsanity.com/paper/1606.00915/) (2016)
- [ShapeNet: An Information-Rich 3D Model Repository](https://mlsanity.com/paper/1512.03012/) (2015)
- [DeepSDF: Learning Continuous Signed Distance Functions for Shape Representation](https://mlsanity.com/paper/1901.05103/) (2019)
- [Scene Representation Networks: Continuous 3D-Structure-Aware Neural Scene Representations](https://mlsanity.com/paper/1906.01618/) (2019)
- [Unpaired Image-to-Image Translation using Cycle-Consistent Adversarial Networks](https://mlsanity.com/paper/1703.10593/) (2017)
- [Keep it SMPL: Automatic Estimation of 3D Human Pose and Shape from a Single Image](https://mlsanity.com/paper/1607.08128/) (2016)
- [Pixel2Mesh: Generating 3D Mesh Models from Single RGB Images](https://mlsanity.com/paper/1804.01654/) (2018)
- [3D-R2N2: A Unified Approach for Single and Multi-view 3D Object Reconstruction](https://mlsanity.com/paper/1604.00449/) (2016)
- [Learning a Probabilistic Latent Space of Object Shapes via 3D Generative-Adversarial Modeling](https://mlsanity.com/paper/1610.07584/) (2016)
- [Deep Metric Learning via Lifted Structured Feature Embedding](https://mlsanity.com/paper/1511.06452/) (2015)
- [PointRend: Image Segmentation as Rendering](https://mlsanity.com/paper/1912.08193/) (2019)
- [Soft Rasterizer: A Differentiable Renderer for Image-based 3D Reasoning](https://mlsanity.com/paper/1904.01786/) (2019)
- [Autoencoding beyond pixels using a learned similarity metric](https://mlsanity.com/paper/1512.09300/) (2015)
- [DeepVoxels: Learning Persistent 3D Feature Embeddings](https://mlsanity.com/paper/1812.01024/) (2018)
- [Learning Category-Specific Mesh Reconstruction from Image Collections](https://mlsanity.com/paper/1803.07549/) (2018)
- [State of the Art on Neural Rendering](https://mlsanity.com/paper/2004.03805/) (2020)
- [What Do Single-view 3D Reconstruction Networks Learn?](https://mlsanity.com/paper/1905.03678/) (2019)
- [Unsupervised Learning of Probably Symmetric Deformable 3D Objects from Images in the Wild](https://mlsanity.com/paper/1911.11130/) (2019)
- [Multi-view Supervision for Single-view Reconstruction via Differentiable Ray Consistency](https://mlsanity.com/paper/1704.06254/) (2017)
- [Learning a Predictable and Generative Vector Representation for Objects](https://mlsanity.com/paper/1603.08637/) (2016)
- [Escaping Plato's Cave: 3D Shape From Adversarial Rendering](https://mlsanity.com/paper/1811.11606/) (2018)
- [Monocular Total Capture: Posing Face, Body, and Hands in the Wild](https://mlsanity.com/paper/1812.01598/) (2018)
- [Self-supervised Single-view 3D Reconstruction via Semantic Consistency](https://mlsanity.com/paper/2003.06473/) (2020)
- [3D Shape Induction from 2D Views of Multiple Objects](https://mlsanity.com/paper/1612.05872/) (2016)
- [Neural Rerendering in the Wild](https://mlsanity.com/paper/1904.04290/) (2019)
- [Large-scale interactive object segmentation with human annotators](https://mlsanity.com/paper/1903.10830/) (2019)

## Built on by (most cited first, 30 of 65)

- [RealFusion: 360deg Reconstruction of Any Object from a Single Image](https://mlsanity.com/paper/2302.10663/) (2023)
- [SparseFusion: Distilling View-conditioned Diffusion for 3D Reconstruction](https://mlsanity.com/paper/2212.00792/) (2022)
- [BANMo: Building Animatable 3D Neural Models from Many Casual Videos](https://mlsanity.com/paper/2112.12761/) (2021)
- [NeRDi: Single-View NeRF Synthesis with Language-Guided Diffusion as General Image Priors](https://mlsanity.com/paper/2212.03267/) (2022)
- [EpiGRAF: Rethinking training of 3D GANs](https://mlsanity.com/paper/2206.10535/) (2022)
- [What's in your hands? 3D Reconstruction of Generic Objects in Hands](https://mlsanity.com/paper/2204.07153/) (2022)
- [LASSIE: Learning Articulated Shapes from Sparse Image Ensemble via 3D Part Discovery](https://mlsanity.com/paper/2207.03434/) (2022)
- [DOVE: Learning Deformable 3D Objects by Watching Videos](https://mlsanity.com/paper/2107.10844/) (2021)
- [Learning the 3D Fauna of the Web](https://mlsanity.com/paper/2401.02400/) (2024)
- [Few-View Object Reconstruction with Unknown Categories and Camera Poses](https://mlsanity.com/paper/2212.04492/) (2022)
- [FiG-NeRF: Figure-Ground Neural Radiance Fields for 3D Object Category Modelling](https://mlsanity.com/paper/2104.08418/) (2021)
- [Reconstructing Animatable Categories from Videos](https://mlsanity.com/paper/2305.06351/) (2023)
- [REACTO: Reconstructing Articulated Objects from a Single Video](https://mlsanity.com/paper/2404.11151/) (2024)
- [MVD-Fusion: Single-view 3D via Depth-consistent Multi-view Generation](https://mlsanity.com/paper/2404.03656/) (2024)
- [De-rendering 3D Objects in the Wild](https://mlsanity.com/paper/2201.02279/) (2022)
- [Hi-LASSIE: High-Fidelity Articulated Shape and Skeleton Discovery from Sparse Image Ensemble](https://mlsanity.com/paper/2212.11042/) (2022)
- [Learning Dexterous Manipulation from Exemplar Object Trajectories and Pre-Grasps](https://mlsanity.com/paper/2209.11221/) (2022)
- [Differentiable Stereopsis: Meshes from multiple views using differentiable rendering](https://mlsanity.com/paper/2110.05472/) (2021)
- [Pre-train, Self-train, Distill: A simple recipe for Supersizing 3D Reconstruction](https://mlsanity.com/paper/2204.03642/) (2022)
- [Share With Thy Neighbors: Single-View Reconstruction by Cross-Instance Consistency](https://mlsanity.com/paper/2204.10310/) (2022)
- [DSO: Aligning 3D Generators with Simulation Feedback for Physical Soundness](https://mlsanity.com/paper/2503.22677/) (2025)
- [Real3D: Scaling Up Large Reconstruction Models with Real-World Images](https://mlsanity.com/paper/2406.08479/) (2024)
- [Self-Supervised Geometric Correspondence for Category-Level 6D Object Pose Estimation in the Wild](https://mlsanity.com/paper/2210.07199/) (2022)
- [ARTIC3D: Learning Robust Articulated 3D Shapes from Noisy Web Image Collections](https://mlsanity.com/paper/2306.04619/) (2023)
- [PICO: Reconstructing 3D People In Contact with Objects](https://mlsanity.com/paper/2504.17695/) (2025)
- [Pixel2Mesh++: 3D Mesh Generation and Refinement from Multi-View Images](https://mlsanity.com/paper/2204.09866/) (2022)
- [Learning 3D Object Shape and Layout without 3D Supervision](https://mlsanity.com/paper/2206.07028/) (2022)
- [DDF-HO: Hand-Held Object Reconstruction via Conditional Directed Distance Field](https://mlsanity.com/paper/2308.08231/) (2023)
- [SAOR: Single-View Articulated Object Reconstruction](https://mlsanity.com/paper/2303.13514/) (2023)
- [ShapeClipper: Scalable 3D Shape Learning from Single-View Images via Geometric and CLIP-based Consistency](https://mlsanity.com/paper/2304.06247/) (2023)

## Abstract (arXiv)

We aim to infer 3D shape and pose of object from a single image and propose a learning-based approach that can train from unstructured image collections, supervised by only segmentation outputs from off-the-shelf recognition systems (i.e. 'shelf-supervised'). We first infer a volumetric representation in a canonical frame, along with the camera pose. We enforce the representation geometrically consistent with both appearance and masks, and also that the synthesized novel views are indistinguishable from image collections. The coarse volumetric prediction is then converted to a mesh-based representation, which is further refined in the predicted camera frame. These two steps allow both shape-pose factorization from image collections and per-instance reconstruction in finer details. We examine the method on both synthetic and real-world datasets and demonstrate its scalability on 50 categories in the wild, an order of magnitude more classes than existing works.