Paper
LiDAR Prompted Spatio-Temporal Multi-View Stereo for Autonomous Driving
Authors
Qihao Sun, Jiarun Liu, Ziqian Ni, Jianyun Xu, Tao Xie, Lijun Zhao, Ruifeng Li, Sheng Yang
Abstract
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.
Metadata
Related papers
Gen-Searcher: Reinforcing Agentic Search for Image Generation
Kaituo Feng, Manyuan Zhang, Shuang Chen, Yunlong Lin, Kaixuan Fan, Yilei Jian... • 2026-03-30
On-the-fly Repulsion in the Contextual Space for Rich Diversity in Diffusion Transformers
Omer Dahary, Benaya Koren, Daniel Garibi, Daniel Cohen-Or • 2026-03-30
Graphilosophy: Graph-Based Digital Humanities Computing with The Four Books
Minh-Thu Do, Quynh-Chau Le-Tran, Duc-Duy Nguyen-Mai, Thien-Trang Nguyen, Khan... • 2026-03-30
ParaSpeechCLAP: A Dual-Encoder Speech-Text Model for Rich Stylistic Language-Audio Pretraining
Anuj Diwan, Eunsol Choi, David Harwath • 2026-03-30
RAD-AI: Rethinking Architecture Documentation for AI-Augmented Ecosystems
Oliver Aleksander Larsen, Mahyar T. Moghaddam • 2026-03-30
Raw Data (Debug)
{
"raw_xml": "<entry>\n <id>http://arxiv.org/abs/2603.03765v1</id>\n <title>LiDAR Prompted Spatio-Temporal Multi-View Stereo for Autonomous Driving</title>\n <updated>2026-03-04T06:22:01Z</updated>\n <link href='https://arxiv.org/abs/2603.03765v1' rel='alternate' type='text/html'/>\n <link href='https://arxiv.org/pdf/2603.03765v1' rel='related' title='pdf' type='application/pdf'/>\n <summary>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:\n (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.</summary>\n <category scheme='http://arxiv.org/schemas/atom' term='cs.CV'/>\n <published>2026-03-04T06:22:01Z</published>\n <arxiv:primary_category term='cs.CV'/>\n <author>\n <name>Qihao Sun</name>\n </author>\n <author>\n <name>Jiarun Liu</name>\n </author>\n <author>\n <name>Ziqian Ni</name>\n </author>\n <author>\n <name>Jianyun Xu</name>\n </author>\n <author>\n <name>Tao Xie</name>\n </author>\n <author>\n <name>Lijun Zhao</name>\n </author>\n <author>\n <name>Ruifeng Li</name>\n </author>\n <author>\n <name>Sheng Yang</name>\n </author>\n </entry>"
}