Sparse-LiDAR Prompting of Monocular Geometry Foundations: An Empirical Study Toward Long-Range Driving Depth

• URL: http://arxiv.org/abs/2605.26456v1
• Date: Tue, 26 May 2026 02:12:15 GMT
• Title: Sparse-LiDAR Prompting of Monocular Geometry Foundations: An Empirical Study Toward Long-Range Driving Depth
• Abstract summary: We present SLIM, the first adaptation of MoGe-2 to accept truly sparse LiDAR input.<n>On Virtual KITTI and CARLA, SLIM reduces the absolute error of the MoGe-2 baseline by approximately 39-51% at 100-150 m.
• Score: 10.469394868633234
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Sparse-LiDAR-prompted depth foundation models (PromptDA, Prior Depth Anything, DMD3C) have shown strong results on indoor scenes or within KITTI's standard 80-meter evaluation cap. However, two limitations remain: (i) systematic distance-stratified evaluation in long-range driving regimes (50-150 m) is largely absent; (ii) prior approaches built on disparity-based foundations rely on pre-interpolated dense priors, leaving truly sparse LiDAR injection on point-map foundations (e.g., MoGe-2, NeurIPS 2025) unexplored. We present SLIM (Sparse-LiDAR Injected Monocular geometry), the first adaptation of MoGe-2 to accept truly sparse LiDAR input. SLIM integrates a partial-convolution sparse encoder with a multi-scale fusion neck that fuses LiDAR features into the point-map decoder at five scales. We adopt density-agnostic training (random injection ratio in [0.005, 0.30]) so a single model serves diverse input densities. On Virtual KITTI and CARLA, SLIM reduces the absolute relative error of the MoGe-2 baseline by approximately 39-51% at 100-150 m. Ablation across six injection ratios shows partial-convolution injection improves both AbsRel and RMSE on Virtual KITTI in all six settings; on CARLA, AbsRel improves in five of six settings (one near-tie at 0.015 differs by 0.0013), and RMSE is comparable across encoders, with partial-convolution improving in three settings (by up to 0.31 unit) and losing by at most 0.11 unit in the other three.

Related papers

• ScopeMamba-YOLO: Widening the Perceptual Scope Inward and Outward for Small Object Detection in Remote Sensing Imagery [2.3496832983179807]
  Small object detection in unmanned aerial vehicle (UAV) and remote sensing imagery requires preserving high-resolution detail while modeling long-range context.<n>We propose ScopeMamba-YOLO, built around an off-path, zero-gated selective-scanning principle that decouples contextual modeling from the convolutional stream.<n>On VisDrone 2019, ScopeMamba-S achieves 50.8% mAP50 with 3.57M parameters, exceeding YOLOv8s by 10.8 pp while using 32% of its parameters; ScopeMamba-M reaches 52.6% mAP50 with 6.48M parameters.
  arXiv  Detail & Related papers  (2026-09-09T13:32:46Z)
• Solution for UCF UrbanTwin LUMPI Track: Sim-to-Real Urban LiDAR 3D Object Detection [54.03436243843709]
  We present our solution to the LUMPI track of the UCF UrbanTwin Sim2Real LiDAR Challenge at the 6th DriveX Workshop, ECCV 2026.<n>The detector must be trained only on synthetic data and is evaluated on 50 held-out real LiDAR frames.<n>A separate 50-frame synthetic submission is evaluated for point-cloud realism.
  arXiv  Detail & Related papers  (2026-09-07T15:03:36Z)
• RadioVIL: Anomaly-Aware Diffusion Models for Radio Map Inpainting and Zero-Shot Vehicle Localization [24.12472362710203]
  High-precision radio map construction is essential for emerging 6G Integrated Sensing and Communication (ISAC) applications.<n>We propose RadioVIL, a framework that reformulates joint radio map inpainting and zero-shot vehicle localization as a prior-guided physical inverse problem.
  arXiv  Detail & Related papers  (2026-08-17T06:34:14Z)
• An Agentic AI Framework Overcomes Fundamental Limitations of Large Language Models for Glaucoma Detection from Fundus Photography [1.3023698730561286]
  Large language models (LLMs) show promise in medical image interpretation but suffer from hallucination, limited accuracy, and run-to-run inconsistency.<n>We developed and validated an agentic AI framework integrating LLMs with specialized deep learning tools for glaucoma detection from fundus photography.
  arXiv  Detail & Related papers  (2026-08-07T17:33:12Z)
• ZipDepth: Bringing Lightweight Zero-Shot Monocular Depth Anywhere, on Any Device [51.39111895181487]
  We present ZipDepth, a compact monocular depth network that bridges the gap between single-domain, self-supervised paradigms and lightweight alternatives.<n>ZipDepth runs at real-time rates from server GPU to power-constrained devices, achieving the best trade-off between zero-shot accuracy and deployment efficiency.
  arXiv  Detail & Related papers  (2026-07-09T17:59:58Z)
• D2-V2X: Depth-Driven Cooperative V2X Reasoning for Autonomous Driving [10.860896159477264]
  We introduce D2-V2X, a spatially-aware Question-Rationale-Answer (QRA) benchmark featuring 8,500 triplets.<n>By enforcing natural language recall rationales prior to structured outputs, our model is forced to explicitly articulate spatial relations.<n>While the model achieves a functional decision-making F1-score of 53.5, we identify 3D-to-2D projection as a fundamental bottleneck in current VLM architectures.
  arXiv  Detail & Related papers  (2026-05-22T18:05:10Z)
• MolmoAct2: Action Reasoning Models for Real-world Deployment [67.6315757474802]
  MolmoAct2 is a fully open action reasoning model built for practical deployment.<n>We introduce MolmoER, a VLM backbone specialized for spatial and embodied reasoning.<n>We release three new datasets spanning low-to-medium cost platforms.
  arXiv  Detail & Related papers  (2026-05-04T17:51:21Z)
• Shower-Aware Dual-Stream Voxel Networks for Structural Defect Detection in Cosmic-Ray Muon Tomography [3.8929279518915862]
  We present SA-DSVN, a 3D convolutional architecture for voxel-level segmentation of structural defects in reinforced concrete.<n>We process scattering kinematics (9 channels) and secondary electromagnetic shower multiplicities (40 channels) through independent encoder streams fused via cross-attention.<n>On 60 independently simulated validation volumes, the model achieves 96.3% voxel accuracy, per-defect Dice scores of 0.59-0.81, and 100% volume-level detection sensitivity at 10 ms inference per volume.
  arXiv  Detail & Related papers  (2026-04-04T14:04:39Z)
• Less is More in Semantic Space: Intrinsic Decoupling via Clifford-M for Fundus Image Classification [13.23226865033351]
  We propose Clifford-M, a lightweight backbone that replaces feed-forward expansion and frequency-splitting modules with sparse geometric interaction.<n>Without pre-training, Clifford-M achieves a mean AUC-ROC of 0.8142 and a mean macro-F1 of 0.5481 on ODIR-5K using only 0.85M parameters.
  arXiv  Detail & Related papers  (2026-03-21T13:00:05Z)
• Structure-Informed Estimation for Pilot-Limited MIMO Channels via Tensor Decomposition [51.56484100374058]
  This paper formulates pilot-limited channel estimation as low-rank tensor completion from sparse observations.<n>Experiments on synthetic channels demonstrate 10-20,dB normalized mean-square error (NMSE) improvement over least-squares (LS)<n> evaluations on DeepMIMO ray-tracing channels show 24-44% additional NMSE reduction over pure tensor-based methods.
  arXiv  Detail & Related papers  (2026-02-03T23:38:05Z)
• LiNeXt: Revisiting LiDAR Completion with Efficient Non-Diffusion Architectures [52.59993476989728]
  LiNeXt is a lightweight, non-diffusion network optimized for rapid and accurate point cloud completion.<n>LiNeXt achieves a 199.8x speedup in inference, reduces Chamfer Distance by 50.7%, and uses only 6.1% of the parameters compared with LiDiff.
  arXiv  Detail & Related papers  (2025-11-13T11:28:18Z)
• LiDAR-VGGT: Cross-Modal Coarse-to-Fine Fusion for Globally Consistent and Metric-Scale Dense Mapping [19.77609066194095]
  Reconstructing large-scale colored point clouds is an important task in robotics, supporting perception, navigation, and scene understanding.<n>We propose LiDAR-VGGT, a novel framework that tightly couples LiDAR inertial odometry with the state-of-the-art VGGT model through a two-stage coarse- to-fine fusion pipeline.<n>Experiments across multiple datasets demonstrate that LiDAR-VGGT achieves dense, globally consistent colored point clouds and outperforms both VGGT-based methods and LIVO baselines.
  arXiv  Detail & Related papers  (2025-11-03T03:24:28Z)
• DIMM: Decoupled Multi-hierarchy Kalman Filter for 3D Object Tracking [50.038098341549095]
  State estimation is challenging for 3D object tracking with high maneuverability.<n>We propose a novel framework, DIMM, to effectively combine estimates from different motion models in each direction.<n>DIMM significantly improves the tracking accuracy of existing state estimation methods by 31.61%99.23%.
  arXiv  Detail & Related papers  (2025-05-18T10:12:41Z)
• Inertial Hallucinations -- When Wearable Inertial Devices Start Seeing Things [82.15959827765325]
  We propose a novel approach to multimodal sensor fusion for Ambient Assisted Living (AAL) We address two major shortcomings of standard multimodal approaches, limited area coverage and reduced reliability. Our new framework fuses the concept of modality hallucination with triplet learning to train a model with different modalities to handle missing sensors at inference time.
  arXiv  Detail & Related papers  (2022-07-14T10:04:18Z)

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.