# Supervised Learning of the Next-Best-View for 3D Object Reconstruction

arXiv: https://arxiv.org/abs/1905.05833 · HTML: https://mlsanity.com/paper/1905.05833/

## Key facts

- Cited by 24 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 14 May 2019.

## Built on by (most cited first, 24 of 24)

- [Uncertainty Guided Policy for Active Robotic 3D Reconstruction using Neural Radiance Fields](https://mlsanity.com/paper/2209.08409/) (2022)
- [Learning Multi-View Aggregation In the Wild for Large-Scale 3D Semantic Segmentation](https://mlsanity.com/paper/2204.07548/) (2022)
- [Active 3D Shape Reconstruction from Vision and Touch](https://mlsanity.com/paper/2107.09584/) (2021)
- [Eye, Robot: Learning to Look to Act with a BC-RL Perception-Action Loop](https://mlsanity.com/paper/2506.10968/) (2025)
- [MACARONS: Mapping And Coverage Anticipation with RGB Online Self-Supervision](https://mlsanity.com/paper/2303.03315/) (2023)
- [SCONE: Surface Coverage Optimization in Unknown Environments by Volumetric Integration](https://mlsanity.com/paper/2208.10449/) (2022)
- [NextBestPath: Efficient 3D Mapping of Unseen Environments](https://mlsanity.com/paper/2502.05378/) (2025)
- [Attention-driven Next-best-view Planning for Efficient Reconstruction of Plants and Targeted Plant Parts](https://mlsanity.com/paper/2206.10274/) (2022)
- [Uncertainty-Driven Active Vision for Implicit Scene Reconstruction](https://mlsanity.com/paper/2210.00978/) (2022)
- [Peering into the Unknown: Active View Selection with Neural Uncertainty Maps for 3D Reconstruction](https://mlsanity.com/paper/2506.14856/) (2025)
- [MAGICIAN: Efficient Long-Term Planning with Imagined Gaussians for Active Mapping](https://mlsanity.com/paper/2603.22650/) (2026)
- [Next-best-view Regression using a 3D Convolutional Neural Network](https://mlsanity.com/paper/2101.09397/) (2021)
- [Exploiting Priors from 3D Diffusion Models for RGB-Based One-Shot View Planning](https://mlsanity.com/paper/2403.16803/) (2024)
- [DM-OSVP++: One-Shot View Planning Using 3D Diffusion Models for Active RGB-Based Object Reconstruction](https://mlsanity.com/paper/2504.11674/) (2025)
- [Deep SIMBAD: Active Landmark-based Self-localization Using Ranking -based Scene Descriptor](https://mlsanity.com/paper/2109.02786/) (2021)
- [Robot Active Neural Sensing and Planning in Unknown Cluttered Environments](https://mlsanity.com/paper/2208.11079/) (2022)
- [SSL-NBV: A Self-Supervised-Learning-Based Next-Best-View algorithm for Efficient 3D Plant Reconstruction by a Robot](https://mlsanity.com/paper/2410.14790/) (2024)
- [Next-Best-View Estimation based on Deep Reinforcement Learning for Active Object Classification](https://mlsanity.com/paper/2110.06766/) (2021)
- [3D Pose Estimation of Tomato Peduncle Nodes using Deep Keypoint Detection and Point Cloud](https://mlsanity.com/paper/2311.04699/) (2023)
- [Next Best View For Point-Cloud Model Acquisition: Bayesian Approximation and Uncertainty Analysis](https://mlsanity.com/paper/2411.01734/) (2024)
- [Boundary Exploration of Next Best View Policy in 3D Robotic Scanning](https://mlsanity.com/paper/2412.10444/) (2024)
- [Camera Splatting for Continuous View Optimization](https://mlsanity.com/paper/2509.15677/) (2025)
- [DA-NBV: A Direction-Aware Next-Best-View Planner for Efficient 3D Reconstruction of Ships at Sea](https://mlsanity.com/paper/2608.08025/) (2026)
- [EyeRobot 2.0: Active Gaze for Precise Manipulation without Wrist Cameras](https://mlsanity.com/paper/2610.03710/) (2026)

## Abstract (arXiv)

Motivated by the advances in 3D sensing technology and the spreading of low-cost robotic platforms, 3D object reconstruction has become a common task in many areas. Nevertheless, the selection of the optimal sensor pose that maximizes the reconstructed surface is a problem that remains open. It is known in the literature as the next-best-view planning problem. In this paper, we propose a novel next-best-view planning scheme based on supervised deep learning. The scheme contains an algorithm for automatic generation of datasets and an original three-dimensional convolutional neural network (3D-CNN) used to learn the next-best-view. Unlike previous work where the problem is addressed as a search, the trained 3D-CNN directly predicts the sensor pose. We present a comparison of the proposed network against a similar net, and we present several experiments of the reconstruction of unknown objects validating the effectiveness of the proposed scheme.