# How Many Views Are Needed to Reconstruct an Unknown Object Using NeRF?

arXiv: https://arxiv.org/abs/2310.00684 · HTML: https://mlsanity.com/paper/2310.00684/

## Key facts

- Cited by 8 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 1 Oct 2023.

## Built on by (most cited first, 8 of 8)

- [VISO-Grasp: Vision-Language Informed Spatial Object-centric 6-DoF Active View Planning and Grasping in Clutter and Invisibility](https://mlsanity.com/paper/2503.12609/) (2025)
- [Exploiting Priors from 3D Diffusion Models for RGB-Based One-Shot View Planning](https://mlsanity.com/paper/2403.16803/) (2024)
- [Enhancing Single Image to 3D Generation using Gaussian Splatting and Hybrid Diffusion Priors](https://mlsanity.com/paper/2410.09467/) (2024)
- [DM-OSVP++: One-Shot View Planning Using 3D Diffusion Models for Active RGB-Based Object Reconstruction](https://mlsanity.com/paper/2504.11674/) (2025)
- [ObjSplat: Geometry-Aware Gaussian Surfels for Active Object Reconstruction](https://mlsanity.com/paper/2601.06997/) (2026)
- [STAIR: Semantic-Targeted Active Implicit Reconstruction](https://mlsanity.com/paper/2403.11233/) (2024)
- [Single-View 3D Reconstruction via SO(2)-Equivariant Gaussian Sculpting Networks](https://mlsanity.com/paper/2409.07245/) (2024)
- [Data Augmentation for NeRFs in the Low Data Limit](https://mlsanity.com/paper/2503.02092/) (2025)

## Abstract (arXiv)

Neural Radiance Fields (NeRFs) are gaining significant interest for online active object reconstruction due to their exceptional memory efficiency and requirement for only posed RGB inputs. Previous NeRF-based view planning methods exhibit computational inefficiency since they rely on an iterative paradigm, consisting of (1) retraining the NeRF when new images arrive; and (2) planning a path to the next best view only. To address these limitations, we propose a non-iterative pipeline based on the Prediction of the Required number of Views (PRV). The key idea behind our approach is that the required number of views to reconstruct an object depends on its complexity. Therefore, we design a deep neural network, named PRVNet, to predict the required number of views, allowing us to tailor the data acquisition based on the object complexity and plan a globally shortest path. To train our PRVNet, we generate supervision labels using the ShapeNet dataset. Simulated experiments show that our PRV-based view planning method outperforms baselines, achieving good reconstruction quality while significantly reducing movement cost and planning time. We further justify the generalization ability of our approach in a real-world experiment.