# Unsupervised Severely Deformed Mesh Reconstruction (DMR) from a Single-View Image

arXiv: https://arxiv.org/abs/2201.09373 · HTML: https://mlsanity.com/paper/2201.09373/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 12 of its 24 references that are in the map.
- First posted on arXiv 23 Jan 2022.

## Builds on (most cited first, 12 of 12)

- [U-Net: Convolutional Networks for Biomedical Image Segmentation](https://mlsanity.com/paper/1505.04597/) (2015)
- [Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks](https://mlsanity.com/paper/1506.01497/) (2015)
- [Accelerating 3D Deep Learning with PyTorch3D](https://mlsanity.com/paper/2007.08501/) (2020)
- [Pixel2Mesh: Generating 3D Mesh Models from Single RGB Images](https://mlsanity.com/paper/1804.01654/) (2018)
- [Soft Rasterizer: A Differentiable Renderer for Image-based 3D Reasoning](https://mlsanity.com/paper/1904.01786/) (2019)
- [Learning Category-Specific Mesh Reconstruction from Image Collections](https://mlsanity.com/paper/1803.07549/) (2018)
- [3D Menagerie: Modeling the 3D shape and pose of animals](https://mlsanity.com/paper/1611.07700/) (2016)
- [Boundary loss for highly unbalanced segmentation](https://mlsanity.com/paper/1812.07032/) (2018)
- [LASR: Learning Articulated Shape Reconstruction from a Monocular Video](https://mlsanity.com/paper/2105.02976/) (2021)
- [Articulation-aware Canonical Surface Mapping](https://mlsanity.com/paper/2004.00614/) (2020)
- [Video-based Hierarchical Species Classification for Longline Fishing Monitoring](https://mlsanity.com/paper/2102.03520/) (2021)
- [Absolute 3D Pose Estimation and Length Measurement of Severely Deformed Fish from Monocular Videos in Longline Fishing](https://mlsanity.com/paper/2102.04639/) (2021)

## Built on by (most cited first, 1 of 1)

- [HCIL: Hierarchical Class Incremental Learning for Longline Fishing Visual Monitoring](https://mlsanity.com/paper/2202.13018/) (2022)

## Abstract (arXiv)

Much progress has been made in the supervised learning of 3D reconstruction of rigid objects from multi-view images or a video. However, it is more challenging to reconstruct severely deformed objects from a single-view RGB image in an unsupervised manner. Although training-based methods, such as specific category-level training, have been shown to successfully reconstruct rigid objects and slightly deformed objects like birds from a single-view image, they cannot effectively handle severely deformed objects and neither can be applied to some downstream tasks in the real world due to the inconsistent semantic meaning of vertices, which are crucial in defining the adopted 3D templates of objects to be reconstructed. In this work, we introduce a template-based method to infer 3D shapes from a single-view image and apply the reconstructed mesh to a downstream task, i.e., absolute length measurement. Without using 3D ground truth, our method faithfully reconstructs 3D meshes and achieves state-of-the-art accuracy in a length measurement task on a severely deformed fish dataset.