# 3D-PSRNet: Part Segmented 3D Point Cloud Reconstruction From a Single Image

arXiv: https://arxiv.org/abs/1810.00461 · HTML: https://mlsanity.com/paper/1810.00461/

## Key facts

- Cited by 12 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 30 Sep 2018.

## Built on by (most cited first, 12 of 12)

- [LASSIE: Learning Articulated Shapes from Sparse Image Ensemble via 3D Part Discovery](https://mlsanity.com/paper/2207.03434/) (2022)
- [Towards High-Fidelity Single-view Holistic Reconstruction of Indoor Scenes](https://mlsanity.com/paper/2207.08656/) (2022)
- [Category-Level Metric Scale Object Shape and Pose Estimation](https://mlsanity.com/paper/2109.00326/) (2021)
- [No-Reference Point Cloud Quality Assessment via Domain Adaptation](https://mlsanity.com/paper/2112.02851/) (2021)
- [Hi-LASSIE: High-Fidelity Articulated Shape and Skeleton Discovery from Sparse Image Ensemble](https://mlsanity.com/paper/2212.11042/) (2022)
- [Discovering 3D Parts from Image Collections](https://mlsanity.com/paper/2107.13629/) (2021)
- [Coherent 3D Scene Diffusion From a Single RGB Image](https://mlsanity.com/paper/2412.10294/) (2024)
- [Local and Global Point Cloud Reconstruction for 3D Hand Pose Estimation](https://mlsanity.com/paper/2112.06389/) (2021)
- [Meta-Sampler: Almost-Universal yet Task-Oriented Sampling for Point Clouds](https://mlsanity.com/paper/2203.16001/) (2022)
- [Multi-Category Mesh Reconstruction From Image Collections](https://mlsanity.com/paper/2110.11256/) (2021)
- [From Images to Point Clouds: An Efficient Solution for Cross-media Blind Quality Assessment without Annotated Training](https://mlsanity.com/paper/2501.13387/) (2025)
- [REPS: Reconstruction-based Point Cloud Sampling](https://mlsanity.com/paper/2403.05047/) (2024)

## Abstract (arXiv)

We propose a mechanism to reconstruct part annotated 3D point clouds of objects given just a single input image. We demonstrate that jointly training for both reconstruction and segmentation leads to improved performance in both the tasks, when compared to training for each task individually. The key idea is to propagate information from each task so as to aid the other during the training procedure. Towards this end, we introduce a location-aware segmentation loss in the training regime. We empirically show the effectiveness of the proposed loss in generating more faithful part reconstructions while also improving segmentation accuracy. We thoroughly evaluate the proposed approach on different object categories from the ShapeNet dataset to obtain improved results in reconstruction as well as segmentation.