HERE: Hierarchical Active Exploration of Radiance Field with Epistemic Uncertainty Minimization

• URL: http://arxiv.org/abs/2601.07242v1
• Date: Mon, 12 Jan 2026 06:23:29 GMT
• Title: HERE: Hierarchical Active Exploration of Radiance Field with Epistemic Uncertainty Minimization
• Authors: Taekbeom Lee, Dabin Kim, Youngseok Jang, H. Jin Kim,
• Abstract summary: We present HERE, an active 3D scene reconstruction framework based on neural radiance fields, enabling high-fidelity implicit mapping.<n>Our approach centers around an active learning strategy for camera trajectory generation, driven by accurate identification of unseen regions.<n>The effectiveness of the proposed method in active 3D reconstruction is demonstrated by achieving higher reconstruction completeness compared to previous approaches.
• Score: 21.297877967566766
• License: http://creativecommons.org/licenses/by-sa/4.0/
• Abstract: We present HERE, an active 3D scene reconstruction framework based on neural radiance fields, enabling high-fidelity implicit mapping. Our approach centers around an active learning strategy for camera trajectory generation, driven by accurate identification of unseen regions, which supports efficient data acquisition and precise scene reconstruction. The key to our approach is epistemic uncertainty quantification based on evidential deep learning, which directly captures data insufficiency and exhibits a strong correlation with reconstruction errors. This allows our framework to more reliably identify unexplored or poorly reconstructed regions compared to existing methods, leading to more informed and targeted exploration. Additionally, we design a hierarchical exploration strategy that leverages learned epistemic uncertainty, where local planning extracts target viewpoints from high-uncertainty voxels based on visibility for trajectory generation, and global planning uses uncertainty to guide large-scale coverage for efficient and comprehensive reconstruction. The effectiveness of the proposed method in active 3D reconstruction is demonstrated by achieving higher reconstruction completeness compared to previous approaches on photorealistic simulated scenes across varying scales, while a hardware demonstration further validates its real-world applicability.

Related papers

• StepVAR: Structure-Texture Guided Pruning for Visual Autoregressive Models [98.72926158261937]
  We propose a training-free token pruning framework for Visual AutoRegressive models.<n>We employ a lightweight high-pass filter to capture local texture details, while leveraging Principal Component Analysis (PCA) to preserve global structural information.<n>To maintain valid next-scale prediction under sparse tokens, we introduce a nearest neighbor feature propagation strategy.
  arXiv  Detail & Related papers  (2026-03-02T11:35:05Z)
• OUGS: Active View Selection via Object-aware Uncertainty Estimation in 3DGS [14.124481717283544]
  OUGS is a principled, physically-grounded uncertainty formulation for 3DGS.<n>Our core innovation is to derive uncertainty directly from the explicit physical parameters of the 3D Gaussian primitives.<n>This foundation allows us to then seamlessly integrate semantic segmentation masks to produce a targeted, object-aware uncertainty score.
  arXiv  Detail & Related papers  (2025-11-12T15:08:46Z)
• Deep Spectral Epipolar Representations for Dense Light Field Reconstruction [0.0]
  This paper introduces a novel Deep Spectral Epipolar Representation (DSER) framework for dense light field reconstruction.<n>The proposed approach exploits frequency-domain correlations across epipolar plane images to enforce global structural coherence.<n>Experiments on the 4D Light Field Benchmark and a diverse set of real-world datasets demonstrate that DSER achieves superior performance in terms of precision, structural consistency, and computational efficiency.
  arXiv  Detail & Related papers  (2025-08-12T12:41:47Z)
• Adaptive Contextual Embedding for Robust Far-View Borehole Detection [2.206623168926072]
  In blasting operations, accurately detecting densely distributed tiny boreholes from far-view imagery is critical for operational safety and efficiency.<n>We propose an adaptive detection approach that builds upon existing architectures (e.g., YOLO) by explicitly leveraging consistent embedding representations derived through exponential moving average (EMA)-based statistical updates.<n>Our method introduces three synergistic components: (1) adaptive augmentation utilizing dynamically updated image statistics to robustly handle illumination and texture variations; (2) embedding stabilization to ensure consistent and reliable feature extraction; and (3) contextual refinement leveraging spatial context for improved detection accuracy.
  arXiv  Detail & Related papers  (2025-05-08T07:25:42Z)
• ActiveSplat: High-Fidelity Scene Reconstruction through Active Gaussian Splatting [12.644175177979196]
  We propose ActiveSplat, an autonomous high-fidelity reconstruction system leveraging Gaussian splatting.<n>The system establishes a unified framework for online mapping, viewpoint selection, and path planning.
  arXiv  Detail & Related papers  (2024-10-29T11:18:04Z)
• Exploring Local Memorization in Diffusion Models via Bright Ending Attention [62.979954692036685]
  "bright ending" (BE) anomaly in text-to-image diffusion models prone to memorizing training images.<n>We propose a simple yet effective method to integrate BE into existing frameworks.
  arXiv  Detail & Related papers  (2024-10-29T02:16:01Z)
• NARUTO: Neural Active Reconstruction from Uncertain Target Observations [30.09067122521648]
  We present NARUTO, a neural active reconstruction system that combines a hybrid neural representation with uncertainty learning. Our system autonomously explores by targeting uncertain observations and reconstructs environments with remarkable completeness and fidelity.
  arXiv  Detail & Related papers  (2024-02-29T00:25:26Z)
• OccNeRF: Advancing 3D Occupancy Prediction in LiDAR-Free Environments [77.0399450848749]
  We propose an OccNeRF method for training occupancy networks without 3D supervision. We parameterize the reconstructed occupancy fields and reorganize the sampling strategy to align with the cameras' infinite perceptive range. For semantic occupancy prediction, we design several strategies to polish the prompts and filter the outputs of a pretrained open-vocabulary 2D segmentation model.
  arXiv  Detail & Related papers  (2023-12-14T18:58:52Z)
• 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)
• Robust Geometry-Preserving Depth Estimation Using Differentiable Rendering [93.94371335579321]
  We propose a learning framework that trains models to predict geometry-preserving depth without requiring extra data or annotations. Comprehensive experiments underscore our framework's superior generalization capabilities. Our innovative loss functions empower the model to autonomously recover domain-specific scale-and-shift coefficients.
  arXiv  Detail & Related papers  (2023-09-18T12:36:39Z)
• Towards Generalizable Deepfake Detection by Primary Region Regularization [52.41801719896089]
  This paper enhances the generalization capability from a novel regularization perspective. Our method consists of two stages, namely the static localization for primary region maps, and the dynamic exploitation of primary region masks. We conduct extensive experiments over three widely used deepfake datasets - DFDC, DF-1.0, and Celeb-DF with five backbones.
  arXiv  Detail & Related papers  (2023-07-24T05:43:34Z)
• Active Implicit Object Reconstruction using Uncertainty-guided Next-Best-View Optimization [1.2268315442962412]
  Actively planning sensor views during object reconstruction is crucial for autonomous mobile robots. We propose a seamless integration of the emerging implicit representation with the active reconstruction task. Our approach effectively improves reconstruction accuracy and efficiency of view planning in active reconstruction tasks.
  arXiv  Detail & Related papers  (2023-03-29T14:42:30Z)
• CPPF++: Uncertainty-Aware Sim2Real Object Pose Estimation by Vote Aggregation [67.12857074801731]
  We introduce a novel method, CPPF++, designed for sim-to-real pose estimation. To address the challenge posed by vote collision, we propose a novel approach that involves modeling the voting uncertainty. We incorporate several innovative modules, including noisy pair filtering, online alignment optimization, and a feature ensemble.
  arXiv  Detail & Related papers  (2022-11-24T03:27:00Z)

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.