LiDAR Prompted Spatio-Temporal Multi-View Stereo for Autonomous Driving
Accurate metric depth is critical for autonomous driving perception and simulation, yet current approaches struggle to achieve high metric accuracy, multi-view and temporal consistency, and cross-domain generalization. To address these challenges, we present DriveMVS, a novel multi-view stereo framework that reconciles these competing objectives through two key insights: (1) Sparse but metrically accurate LiDAR observations can serve as geometric prompts to anchor depth estimation in absolute scale, and (2) deep fusion of diverse cues is essential for resolving ambiguities and enhancing robustness, while a spatio-temporal decoder ensures consistency across frames. Built upon these principles, DriveMVS embeds the LiDAR prompt in two ways: as a hard geometric prior that anchors the cost volume, and as soft feature-wise guidance fused by a triple-cue combiner. Regarding temporal consistency, DriveMVS employs a spatio-temporal decoder that jointly leverages geometric cues from the MVS cost volume and temporal context from neighboring frames. Experiments show that DriveMVS achieves state-of-the-art performance on multiple benchmarks, excelling in metric accuracy, temporal stability, and zero-shot cross-domain transfer, demonstrating its practical value for scalable, reliable autonomous driving systems.
Code (0)
등록된 구현이 없습니다.
Tasks
Domain GeneralizationAutonomous DrivingDepth EstimationSimilar Papers 제목 키워드 기반
Bootstrapping a 4D LiDAR Annotation Tool from Video Foundation Models
Progress in 4D LiDAR segmentation is bottlenecked by data. Assigning temporally consistent labels across sparse point cloud sequences is costly and hard to scale, and every new task or domain tends to demand fresh dense …
Scene UnderstandingVideo SegmentationAnyView: Synthesizing Any Novel View in Dynamic Scenes
Modern generative video models excel at producing convincing, high-quality outputs, but struggle to maintain multi-view and spatiotemporal consistency in highly dynamic real-world environments. In this work, we introduce…
Video GenerationMVFuseNet: Improving End-to-End Object Detection and Motion Forecasting through Multi-View Fusion of LiDAR Data
In this work, we propose \textit{MVFuseNet}, a novel end-to-end method for joint object detection and motion forecasting from a temporal sequence of LiDAR data. Most existing methods operate in a single view by projectin…
Motion Forecastingobject-detectionObject DetectionGSPR: Multimodal Place Recognition Using 3D Gaussian Splatting for Autonomous Driving
Place recognition is a crucial module to ensure autonomous vehicles obtain usable localization information in GPS-denied environments. In recent years, multimodal place recognition methods have gained increasing attentio…
Autonomous DrivingAutonomous VehiclesSuperFlow++: Enhanced Spatiotemporal Consistency for Cross-Modal Data Pretraining
LiDAR representation learning has emerged as a promising approach to reducing reliance on costly and labor-intensive human annotations. While existing methods primarily focus on spatial alignment between LiDAR and camera…
Autonomous DrivingComputational EfficiencyContrastive LearningRepresentation Learning+1