CVDN

The CVDN dataset is a large-scale video-instruction framework derived from web-based room tour videos, used to evaluate Vision-and-Language Navigation by providing diverse, realistic indoor settings with enriched trajectories for training agents.

Papers using CVDN (3)

Implicit Geometry Representations for Vision-and-Language Navigation from Web Videos2026CoNav: Collaborative Cross-Modal Reasoning for Embodied Navigation2025RoomTour3D: Geometry-Aware Video-Instruction Tuning for Embodied Navigation2024