GO-PRE: Goal-Oriented Next-Best-View Selection via Predictive Rendering Entropy for Active 3D Reconstruction
Quick Answer
GO-PRE introduces a goal-oriented next-best-view selection framework for active 3D reconstruction, optimizing predictive entropy to enhance reconstruction fidelity.
Quick Take
It allows real-time computation of information gain and outperforms existing methods in uncertainty quantification across various benchmarks.
Key Points
- GO-PRE maximizes information gain in the prediction space for active 3D reconstruction.
- The framework supports interactive goal specification for user-defined target views.
- Extensive experiments show GO-PRE improves reconstruction performance significantly.
- Real-time computation of information gain is a key feature of GO-PRE.
- GO-PRE provides more reliable uncertainty quantification than state-of-the-art methods.
Paper Resources
📖 Reader Mode
~2 min readAbstract:Active 3D reconstruction relies on active view selection to maximize reconstruction fidelity under limited capture budgets. However, most existing methods rely on surrogate signals such as parameter uncertainty or geometric heuristics, but these signals are often misaligned with the ultimate goal: the fidelity of rendered predictions. We propose GO-PRE, a goal-oriented next-best-view selection framework that explicitly targets information gain in the prediction space. Specifically, we formulate the objective as maximizing the reduction of the average marginal predictive entropy over a user-specified target view manifold. GO-PRE supports interactive goal specification and yields an efficient acquisition rule that enables real-time computation of information gain. Extensive experiments across benchmarks demonstrate that GO-PRE consistently improves active reconstruction performance and provides more reliable uncertainty quantification compared to state-of-the-art methods.
| Comments: | Accepted at the 43rd International Conference on Machine Learning (ICML 2026) |
| Subjects: | Computer Vision and Pattern Recognition (cs.CV) |
| Cite as: | arXiv:2607.29037 [cs.CV] |
| (or arXiv:2607.29037v1 [cs.CV] for this version) | |
| https://doi.org/10.48550/arXiv.2607.29037 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Yan Song [view email]
[v1]
Fri, 31 Jul 2026 05:29:04 UTC (2,385 KB)
— Originally published at arxiv.org
Want this in your inbox every morning?
Daily brief at your local 8am — bilingual EN/中文, free.
More from arXiv cs.CV
See more →ProMoE-FL: Prototype-conditioned Mixture of Experts for Multimodal Federated Learning with Missing Modalities
ProMoE-FL introduces a Prototype-conditioned Mixture-of-Experts framework for multimodal federated learning, effectively addressing missing modalities. It outperforms existing methods on four chest X-ray datasets, demonstrating superior feature synthesis capabilities in both homogeneous and heterogeneous settings.