Research map / 3D vision / NeRF and radiance fields
Spectral-Geometric Neural Fields for Pose-Free LiDAR View Synthesis
Yinuo Jiang, Jun Cheng, Yiran Wang, Cheng Cheng
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| add spectral embeddings to geometric encodings (hybrid representation) (ablation) | SG-NLF · nuScenes low-frequency | Chamfer Distance: 0.217 -> 0.155 | Improved |
| add global pose optimization (confidence-aware graph) (ablation) | SG-NLF · nuScenes low-frequency | ATE (m): 0.798 -> 0.071 | Improved |
| add cross-frame consistency adversarial loss (ablation) | SG-NLF · nuScenes low-frequency | Chamfer Distance: 0.182 -> 0.155 | Improved |
| add cross-frame consistency adversarial loss (ablation) | SG-NLF · nuScenes low-frequency | ATE (m): 0.076 -> 0.071 | Improved |
| add geometric encodings to spectral embeddings (ablation) | SG-NLF · nuScenes low-frequency | Chamfer Distance: 0.181 -> 0.155 | Improved |
| spectral-only embeddings replacing hash-grid interpolation (w/o GE vs GeoNLF) (ablation) | SG-NLF · nuScenes low-frequency | Chamfer Distance: 0.241 -> 0.181 | Improved |
| cross-frame consistency alone without pose optimization (ablation) | Baseline · nuScenes low-frequency | Chamfer Distance: 0.618 -> 0.463 | Improved |
| SG-NLF vs GeoNLF on rotation error | SG-NLF · nuScenes pose estimation | RPEr (deg): 0.103 -> 0.158 | Hurt |
| replace pose-free GeoNLF with SG-NLF | LiDAR view synthesis · KITTI-360 standard-frequency | Chamfer Distance: 0.0894 -> 0.0867 | Improved |
Closest papers by meaning
- GeoNLF: Geometry guided Pose-Free Neural LiDAR Fields (NeurIPS 2024 · similarity 0.91)
- STGC-NeRF: Spatial-Temporal Geometric Consistency for LiDAR Neural Radiance Fields in Dynamic Scenes (AAAI 2025 · similarity 0.91)
- LiDAR4D: Dynamic Neural Fields for Novel Space-time View LiDAR Synthesis (CVPR 2024 · similarity 0.91)
- LidaRF: Delving into Lidar for Neural Radiance Field on Street Scenes (CVPR 2024 · similarity 0.87)
- GS-LiDAR: Generating Realistic LiDAR Point Clouds with Panoramic Gaussian Splatting (ICLR 2025 · similarity 0.87)
- AlignMiF: Geometry-Aligned Multimodal Implicit Field for LiDAR-Camera Joint Synthesis (CVPR 2024 · similarity 0.87)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.
