Neural implicit representations provide memory-efficient signed distance field (SDF) parameterizations for large-scale LiDAR scenes, but the geometry recovered from sparse and often noisy inputs carri...
arXiv:2608.15933v1 Announce Type: cross Abstract: Implicit surface representations have regained popularity because of their use in machine learning. A common component in optimization is regularizat...
arXiv:2610.18005v2 Announce Type: replace Abstract: Surface reconstruction from range scans is challenging in the presence of noise and outliers, as fidelity to observations must be balanced against...
arXiv:2608. 07106v1 Announce Type: new Abstract: Deploying three-dimensional deep learning frameworks to low-power embedded processors is bottlenecked by the unstructured nature of spatial data and the resource-intensive distance sorting algorithms often used before neural network inference.
arXiv:2607. 26645v1 Announce Type: cross Abstract: Existing point-based generative methods for outdoor scenes primarily focus on LiDAR-conditioned completion.
arXiv:2610.19786v1 Announce Type: new Abstract: Generating LiDAR point clouds from multi-view camera images is a valuable task with applications in controllable data synthesis, cross-modal simulation...
NeuDonatello is a new framework for neural signed distance function (SDF) learning that explicitly models spatially varying uncertainty using Monte Carlo sampling. By incorporating this uncertainty into an adaptive regularization scheme and an uncertainty-aware SDF-to-density conversion, the method selectively strengthens geometric constraints where RGB supervision is unreliable, thereby improving surface reconstruction accuracy. Experiments show that NeuDonatello achieves state‑of‑the‑art results on diverse scenes using only posed RGB images.
arXiv:2605.10360v3 Announce Type: replace Abstract: While novel view synthesis (NVS) for dynamic scenes has seen significant progress, reconstructing temporally consistent geometric surfaces remains...
The paper introduces SVRecon, a generalizable neural surface reconstruction framework that uses sparse volumetric representations to achieve high-resolution 3D reconstruction. It employs a two-stage architecture: first predicting occupied voxels with an occupancy network, then rendering only within those regions using specialized sparse algorithms. This approach allows reconstruction at resolutions up to 512³ on 32 GB hardware, producing smoother and more precise surfaces, especially in sparse-view scenarios.
FounRef is a training‑free method that refines frozen monocular foundation priors into dense metric depth by aligning them with sparse metric anchors. It validates anchors against the prior’s predictions, rejects misaligned ones, and applies a structure‑preserving solver to correct depth globally and locally while preserving fine geometry. The approach works out of the box on unseen cameras and scenes, achieving up to 24% lower depth error, 92% lower surface‑normal noise, and nearly 15× faster inference than a leading depth‑completion network.
arXiv:2609.05744v1 Announce Type: cross Abstract: Reconstructing continuous terrain manifolds from massive, unstructured airborne LiDAR point clouds remains challenging in complex Wildland-Urban Inte...
arXiv:2610.19201v1 Announce Type: new Abstract: We present LidarVerse, a real-time unified LiDAR world model for sensor simulation across tasks and sensors. Existing LiDAR simulators largely follow o...