Peering into the Unknown: Active View Selection with Neural Uncertainty Maps for 3D Reconstruction

• URL: http://arxiv.org/abs/2506.14856v1
• Date: Tue, 17 Jun 2025 08:15:52 GMT
• Title: Peering into the Unknown: Active View Selection with Neural Uncertainty Maps for 3D Reconstruction
• Authors: Zhengquan Zhang, Feng Xu, Mengmi Zhang,
• Abstract summary: Active view selection (AVS) for 3D reconstruction remains a fundamental challenge in computer vision.<n>We introduce a novel AVS approach guided by neural uncertainty maps predicted by a lightweight feedforward deep neural network, named UPNet.<n>We train 3D rendering models and evaluate the quality of novel view against other competitive AVS methods.
• Score: 10.51717081118357
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Some perspectives naturally provide more information than others. How can an AI system determine which viewpoint offers the most valuable insight for accurate and efficient 3D object reconstruction? Active view selection (AVS) for 3D reconstruction remains a fundamental challenge in computer vision. The aim is to identify the minimal set of views that yields the most accurate 3D reconstruction. Instead of learning radiance fields, like NeRF or 3D Gaussian Splatting, from a current observation and computing uncertainty for each candidate viewpoint, we introduce a novel AVS approach guided by neural uncertainty maps predicted by a lightweight feedforward deep neural network, named UPNet. UPNet takes a single input image of a 3D object and outputs a predicted uncertainty map, representing uncertainty values across all possible candidate viewpoints. By leveraging heuristics derived from observing many natural objects and their associated uncertainty patterns, we train UPNet to learn a direct mapping from viewpoint appearance to uncertainty in the underlying volumetric representations. Next, our approach aggregates all previously predicted neural uncertainty maps to suppress redundant candidate viewpoints and effectively select the most informative one. Using these selected viewpoints, we train 3D neural rendering models and evaluate the quality of novel view synthesis against other competitive AVS methods. Remarkably, despite using half of the viewpoints than the upper bound, our method achieves comparable reconstruction accuracy. In addition, it significantly reduces computational overhead during AVS, achieving up to a 400 times speedup along with over 50\% reductions in CPU, RAM, and GPU usage compared to baseline methods. Notably, our approach generalizes effectively to AVS tasks involving novel object categories, without requiring any additional training.

Related papers

• Boundary Exploration of Next Best View Policy in 3D Robotic Scanning [6.961253535504979]
  We propose an NBV policy in which the next view explores the boundary of the scanned point cloud.<n>A model-based approach is proposed where the next sensor positions are searched iteratively based on a reference model.<n>A deep learning network, Boundary Exploration NBV network (BENBV-Net), is designed and proposed, which can be used to predict the NBV directly from the scanned data.
  arXiv  Detail & Related papers  (2024-12-11T16:11:13Z)
• Frequency-based View Selection in Gaussian Splatting Reconstruction [9.603843571051744]
  We investigate the problem of active view selection to perform 3D Gaussian Splatting reconstructions with as few input images as possible. By ranking the potential views in the frequency domain, we are able to effectively estimate the potential information gain of new viewpoints. Our method achieves state-of-the-art results in view selection, demonstrating its potential for efficient image-based 3D reconstruction.
  arXiv  Detail & Related papers  (2024-09-24T21:44:26Z)
• Leveraging Neural Radiance Fields for Uncertainty-Aware Visual Localization [56.95046107046027]
  We propose to leverage Neural Radiance Fields (NeRF) to generate training samples for scene coordinate regression. Despite NeRF's efficiency in rendering, many of the rendered data are polluted by artifacts or only contain minimal information gain.
  arXiv  Detail & Related papers  (2023-10-10T20:11:13Z)
• S-VolSDF: Sparse Multi-View Stereo Regularization of Neural Implicit Surfaces [75.30792581941789]
  Neural rendering of implicit surfaces performs well in 3D vision applications. When only sparse input images are available, output quality drops significantly due to the shape-radiance ambiguity problem. We propose to regularize neural rendering optimization with an MVS solution.
  arXiv  Detail & Related papers  (2023-03-30T21:10:58Z)
• Multi-View Photometric Stereo Revisited [100.97116470055273]
  Multi-view photometric stereo (MVPS) is a preferred method for detailed and precise 3D acquisition of an object from images. We present a simple, practical approach to MVPS, which works well for isotropic as well as other object material types such as anisotropic and glossy. The proposed approach shows state-of-the-art results when tested extensively on several benchmark datasets.
  arXiv  Detail & Related papers  (2022-10-14T09:46:15Z)
• Uncertainty Guided Policy for Active Robotic 3D Reconstruction using Neural Radiance Fields [82.21033337949757]
  This paper introduces a ray-based volumetric uncertainty estimator, which computes the entropy of the weight distribution of the color samples along each ray of the object's implicit neural representation. We show that it is possible to infer the uncertainty of the underlying 3D geometry given a novel view with the proposed estimator. We present a next-best-view selection policy guided by the ray-based volumetric uncertainty in neural radiance fields-based representations.
  arXiv  Detail & Related papers  (2022-09-17T21:28:57Z)
• NeurAR: Neural Uncertainty for Autonomous 3D Reconstruction [64.36535692191343]
  Implicit neural representations have shown compelling results in offline 3D reconstruction and also recently demonstrated the potential for online SLAM systems. This paper addresses two key challenges: 1) seeking a criterion to measure the quality of the candidate viewpoints for the view planning based on the new representations, and 2) learning the criterion from data that can generalize to different scenes instead of hand-crafting one. Our method demonstrates significant improvements on various metrics for the rendered image quality and the geometry quality of the reconstructed 3D models when compared with variants using TSDF or reconstruction without view planning.
  arXiv  Detail & Related papers  (2022-07-22T10:05:36Z)
• 2D GANs Meet Unsupervised Single-view 3D Reconstruction [21.93671761497348]
  controllable image generation based on pre-trained GANs can benefit a wide range of computer vision tasks. We propose a novel image-conditioned neural implicit field, which can leverage 2D supervisions from GAN-generated multi-view images. The effectiveness of our approach is demonstrated through superior single-view 3D reconstruction results of generic objects.
  arXiv  Detail & Related papers  (2022-07-20T20:24:07Z)
• Vision Transformer for NeRF-Based View Synthesis from a Single Input Image [49.956005709863355]
  We propose to leverage both the global and local features to form an expressive 3D representation. To synthesize a novel view, we train a multilayer perceptron (MLP) network conditioned on the learned 3D representation to perform volume rendering. Our method can render novel views from only a single input image and generalize across multiple object categories using a single model.
  arXiv  Detail & Related papers  (2022-07-12T17:52:04Z)
• Next-best-view Regression using a 3D Convolutional Neural Network [0.9449650062296823]
  We propose a data-driven approach to address the next-best-view problem. The proposed approach trains a 3D convolutional neural network with previous reconstructions in order to regress the btxtposition of the next-best-view. We have validated the proposed approach making use of two groups of experiments.
  arXiv  Detail & Related papers  (2021-01-23T01:50:26Z)
• Disp R-CNN: Stereo 3D Object Detection via Shape Prior Guided Instance Disparity Estimation [51.17232267143098]
  We propose a novel system named Disp R-CNN for 3D object detection from stereo images. We use a statistical shape model to generate dense disparity pseudo-ground-truth without the need of LiDAR point clouds. Experiments on the KITTI dataset show that, even when LiDAR ground-truth is not available at training time, Disp R-CNN achieves competitive performance and outperforms previous state-of-the-art methods by 20% in terms of average precision.
  arXiv  Detail & Related papers  (2020-04-07T17:48:45Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.