GeoNLF: Geometry guided Pose-Free Neural LiDAR Fields

• URL: http://arxiv.org/abs/2407.05597v1
• Date: Mon, 8 Jul 2024 04:19:49 GMT
• Title: GeoNLF: Geometry guided Pose-Free Neural LiDAR Fields
• Authors: Weiyi Xue, Zehan Zheng, Fan Lu, Haiyun Wei, Guang Chen, Changjun Jiang,
• Abstract summary: We propose a hybrid framework performing alternately global neural reconstruction and pure geometric pose optimization. Experiments on NuScenes and KITTI-360 datasets demonstrate the superiority of GeoNLF in both novel view synthesis and multi-view registration.
• Score: 10.753993328978542
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Although recent efforts have extended Neural Radiance Fields (NeRF) into LiDAR point cloud synthesis, the majority of existing works exhibit a strong dependence on precomputed poses. However, point cloud registration methods struggle to achieve precise global pose estimation, whereas previous pose-free NeRFs overlook geometric consistency in global reconstruction. In light of this, we explore the geometric insights of point clouds, which provide explicit registration priors for reconstruction. Based on this, we propose Geometry guided Neural LiDAR Fields(GeoNLF), a hybrid framework performing alternately global neural reconstruction and pure geometric pose optimization. Furthermore, NeRFs tend to overfit individual frames and easily get stuck in local minima under sparse-view inputs. To tackle this issue, we develop a selective-reweighting strategy and introduce geometric constraints for robust optimization. Extensive experiments on NuScenes and KITTI-360 datasets demonstrate the superiority of GeoNLF in both novel view synthesis and multi-view registration of low-frequency large-scale point clouds.

Related papers

• SGCNeRF: Few-Shot Neural Rendering via Sparse Geometric Consistency Guidance [106.0057551634008]
  FreeNeRF attempts to overcome this limitation by integrating implicit geometry regularization. New study introduces a novel feature matching based sparse geometry regularization module. module excels in pinpointing high-frequency keypoints, thereby safeguarding the integrity of fine details.
  arXiv  Detail & Related papers  (2024-04-01T08:37:57Z)
• Stable Surface Regularization for Fast Few-Shot NeRF [76.00444039563581]
  We develop a stable surface regularization technique called Annealing Signed Distance Function (ASDF) We observe that the Eikonal loss requires dense training signal to shape different level-sets of SDF, leading to low-fidelity results under few-shot training. The proposed approach is up to 45 times faster than existing few-shot novel view synthesis methods.
  arXiv  Detail & Related papers  (2024-03-29T05:39:47Z)
• DeepRicci: Self-supervised Graph Structure-Feature Co-Refinement for Alleviating Over-squashing [72.70197960100677]
  Graph Structure Learning (GSL) plays an important role in boosting Graph Neural Networks (GNNs) with a refined graph. GSL solutions usually focus on structure refinement with task-specific supervision (i.e., node classification) or overlook the inherent weakness of GNNs themselves. We propose to study self-supervised graph structure-feature co-refinement for effectively alleviating the issue of over-squashing in typical GNNs.
  arXiv  Detail & Related papers  (2024-01-23T14:06:08Z)
• NeuSurf: On-Surface Priors for Neural Surface Reconstruction from Sparse Input Views [41.03837477483364]
  We propose a novel sparse view reconstruction framework that leverages on-surface priors to achieve highly faithful surface reconstruction. Specifically, we design several constraints on global geometry alignment and local geometry refinement for jointly optimizing coarse shapes and fine details. The experimental results with DTU and BlendedMVS datasets in two prevalent sparse settings demonstrate significant improvements over the state-of-the-art methods.
  arXiv  Detail & Related papers  (2023-12-21T16:04:45Z)
• NeRF-LOAM: Neural Implicit Representation for Large-Scale Incremental LiDAR Odometry and Mapping [14.433784957457632]
  We propose a novel NeRF-based LiDAR odometry and mapping approach, NeRF-LOAM, consisting of three modules neural odometry, neural mapping, and mesh reconstruction. Our approach achieves state-of-the-art odometry and mapping performance, as well as a strong generalization in large-scale environments utilizing LiDAR data.
  arXiv  Detail & Related papers  (2023-03-19T16:40:36Z)
• GARF:Geometry-Aware Generalized Neural Radiance Field [47.76524984421343]
  We propose Geometry-Aware Generalized Neural Radiance Field (GARF) with a geometry-aware dynamic sampling (GADS) strategy. Our framework infers the unseen scenes on both pixel-scale and geometry-scale with only a few input images. Experiments on indoor and outdoor datasets show that GARF reduces samples by more than 25%, while improving rendering quality and 3D geometry estimation.
  arXiv  Detail & Related papers  (2022-12-05T14:00:59Z)
• MonoSDF: Exploring Monocular Geometric Cues for Neural Implicit Surface Reconstruction [72.05649682685197]
  State-of-the-art neural implicit methods allow for high-quality reconstructions of simple scenes from many input views. This is caused primarily by the inherent ambiguity in the RGB reconstruction loss that does not provide enough constraints. Motivated by recent advances in the area of monocular geometry prediction, we explore the utility these cues provide for improving neural implicit surface reconstruction.
  arXiv  Detail & Related papers  (2022-06-01T17:58:15Z)
• PVSeRF: Joint Pixel-, Voxel- and Surface-Aligned Radiance Field for Single-Image Novel View Synthesis [52.546998369121354]
  We present PVSeRF, a learning framework that reconstructs neural radiance fields from single-view RGB images. We propose to incorporate explicit geometry reasoning and combine it with pixel-aligned features for radiance field prediction. We show that the introduction of such geometry-aware features helps to achieve a better disentanglement between appearance and geometry.
  arXiv  Detail & Related papers  (2022-02-10T07:39:47Z)
• High-Order Residual Network for Light Field Super-Resolution [39.93400777363467]
  Plenoptic cameras usually sacrifice the spatial resolution of their SAIss to acquire information from different viewpoints. We propose a novel high-order residual network to learn the geometric features hierarchically from the light field for reconstruction. Our approach enables high-quality reconstruction even in challenging regions and outperforms state-of-the-art single image or LF reconstruction methods with both quantitative measurements and visual evaluation.
  arXiv  Detail & Related papers  (2020-03-29T18:06:05Z)

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.