ViSE: A Systematic Approach to Vision-Only Street-View Extrapolation
Realistic view extrapolation is critical for closed-loop simulation in autonomous driving, yet it remains a significant challenge for current Novel View Synthesis (NVS) methods, which often produce distorted and inconsistent images beyond the original trajectory. This report presents our winning solution which ctook first place in the RealADSim Workshop NVS track at ICCV 2025. To address the core challenges of street view extrapolation, we introduce a comprehensive four-stage pipeline. First, we employ a data-driven initialization strategy to generate a robust pseudo-LiDAR point cloud, avoiding local minima. Second, we inject strong geometric priors by modeling the road surface with a novel dimension-reduced SDF termed 2D-SDF. Third, we leverage a generative prior to create pseudo ground truth for extrapolated viewpoints, providing auxilary supervision. Finally, a data-driven adaptation network removes time-specific artifacts. On the RealADSim-NVS benchmark, our method achieves a final score of 0.441, ranking first among all participants.
Code (0)
등록된 구현이 없습니다.
Tasks
Novel View SynthesisAutonomous DrivingSimilar Papers 제목 키워드 기반
m2sv: A Scalable Benchmark for Map-to-Street-View Spatial Reasoning
Vision--language models (VLMs) achieve strong performance on many multimodal benchmarks but remain brittle on spatial reasoning tasks that require aligning abstract overhead representations with egocentric views. We intr…
Reinforcement LearningSpatial ReasoningDamageArbiter: A Multimodal Arbitration Framework for Disaster Damage Assessment from Street-View Imagery
Analyzing street-view imagery with computer vision models offers a promising approach for rapid, hyperlocal disaster damage assessment, but existing approaches typically rely on black-box pre-trained vision models, which…
Learning Street View Representations with Spatiotemporal Contrast
Street view imagery is extensively utilized in representation learning for urban visual environments, supporting various sustainable development tasks such as environmental perception and socio-economic assessment. Howev…
Contrastive LearningRepresentation LearningSelf-Supervised LearningVisual Place RecognitionArtifacts of Idiosyncracy in Global Street View Data
Street view data is increasingly being used in computer vision applications in recent years. Machine learning datasets are collected for these applications using simple sampling techniques. These datasets are assumed to …
Street Review: A Participatory AI-Based Framework for Assessing Streetscape Inclusivity
Urban centers undergo social, demographic, and cultural changes that shape public street use and require systematic evaluation of public spaces. This study presents Street Review, a mixed-methods approach that combines p…