dorsal/arxiv
View SchemaR3-RECON: Radiance-Field-Free Active Reconstruction via Renderability
| Authors | Xiaofeng Jin, Matteo Frosi, Yiran Guo, Matteo Matteucci |
|---|---|
| Categories | |
| ArXiv ID | 2601.07484vv1 |
| URL | https://arxiv.org/abs/2601.07484 |
| License | http://arxiv.org/licenses/nonexclusive-distrib/1.0/ |
Abstract
In active reconstruction, an embodied agent must decide where to look next to efficiently acquire views that support high-quality novel-view rendering. Recent work on active view planning for neural rendering largely derives next-best-view (NBV) criteria by backpropagating through radiance fields or estimating information entropy over 3D Gaussian primitives. While effective, these strategies tightly couple view selection to heavy, representation-specific mechanisms and fail to account for the computational and resource constraints required for lightweight online deployment. In this paper, we revisit active reconstruction from a renderability-centric perspective. We propose $\mathbb{R}^{3}$-RECON, a radiance-fields-free active reconstruction framework that induces an implicit, pose-conditioned renderability field over SE(3) from a lightweight voxel map. Our formulation aggregates per-voxel online observation statistics into a unified scalar renderability score that is cheap to update and can be queried in closed form at arbitrary candidate viewpoints in milliseconds, without requiring gradients or radiance-field training. This renderability field is strongly correlated with image-space reconstruction error, naturally guiding NBV selection. We further introduce a panoramic extension that estimates omnidirectional (360$^\circ$) view utility to accelerate candidate evaluation. In the standard indoor Replica dataset, $\mathbb{R}^{3}$-RECON achieves more uniform novel-view quality and higher 3D Gaussian splatting (3DGS) reconstruction accuracy than recent active GS baselines with matched view and time budgets.
{
"annotation_id": "cd7c1dc1-bbf1-45fe-8b0b-0bb661d1abbe",
"date_created": "2026-02-17T05:53:12.073000Z",
"date_modified": "2026-02-17T05:53:12.073000Z",
"file_hash": "43ce638a80450b1c29b39d03c5697b86c6d5f965b957cf30e072544bc8eab3de",
"private": false,
"record": {
"abstract": "In active reconstruction, an embodied agent must decide where to look next to efficiently acquire views that support high-quality novel-view rendering. Recent work on active view planning for neural rendering largely derives next-best-view (NBV) criteria by backpropagating through radiance fields or estimating information entropy over 3D Gaussian primitives. While effective, these strategies tightly couple view selection to heavy, representation-specific mechanisms and fail to account for the computational and resource constraints required for lightweight online deployment. In this paper, we revisit active reconstruction from a renderability-centric perspective. We propose $\\mathbb{R}^{3}$-RECON, a radiance-fields-free active reconstruction framework that induces an implicit, pose-conditioned renderability field over SE(3) from a lightweight voxel map. Our formulation aggregates per-voxel online observation statistics into a unified scalar renderability score that is cheap to update and can be queried in closed form at arbitrary candidate viewpoints in milliseconds, without requiring gradients or radiance-field training. This renderability field is strongly correlated with image-space reconstruction error, naturally guiding NBV selection. We further introduce a panoramic extension that estimates omnidirectional (360$^\\circ$) view utility to accelerate candidate evaluation. In the standard indoor Replica dataset, $\\mathbb{R}^{3}$-RECON achieves more uniform novel-view quality and higher 3D Gaussian splatting (3DGS) reconstruction accuracy than recent active GS baselines with matched view and time budgets.",
"arxiv_id": "2601.07484",
"authors": [
"Xiaofeng Jin",
"Matteo Frosi",
"Yiran Guo",
"Matteo Matteucci"
],
"categories": [
"cs.GR"
],
"license": "http://arxiv.org/licenses/nonexclusive-distrib/1.0/",
"title": "R3-RECON: Radiance-Field-Free Active Reconstruction via Renderability",
"url": "https://arxiv.org/abs/2601.07484",
"version": "v1"
},
"schema_id": "dorsal/arxiv",
"source": {
"execution_id": "9bed73bf-944d-47a0-8f31-40ad023051ef",
"id": "arXiv Dataset",
"type": "Model",
"variant": "snapshot-2026-01-17",
"version": "0.1.0"
},
"user_id": 1000002
}