6Img-to-3D: Few-Image Large-Scale Outdoor Driving Scene Reconstruction

arXiv:2404.12378v1 Announce Type: cross
Abstract: Current 3D reconstruction techniques struggle to infer unbounded scenes from a few images faithfully. Specifically, existing methods have high computational demands, require detailed pose information, and cannot reconstruct occluded regions reliably. We introduce 6Img-to-3D, an efficient, scalable transformer-based encoder-renderer method for single-shot image to 3D reconstruction. Our method outputs a 3D-consistent parameterized triplane from only six outward-facing input images for large-scale, unbounded outdoor driving scenarios. We take a step towards resolving existing shortcomings by combining …

arxiv cs.ai cs.cv cs.lg driving image scale type