Saved in:
Bibliographic Details
Main Authors: Lan, Yatong, Tang, Rongkui, He, Lei
Format: Preprint
Published: 2026
Subjects:
Online Access:https://arxiv.org/abs/2604.07250
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866911576816091136
author Lan, Yatong
Tang, Rongkui
He, Lei
author_facet Lan, Yatong
Tang, Rongkui
He, Lei
contents Extrapolative novel view synthesis can reduce camera-rig dependency in autonomous driving by generating standardized virtual views from heterogeneous sensors. Existing methods degrade outside recorded trajectories because extrapolated poses provide weak geometric support and no dense target-view supervision. The key is to explicitly expose the model to out-of-trajectory condition defects during training. We propose Geo-EVS, a geometry-conditioned framework under sparse supervision. Geo-EVS has two components. Geometry-Aware Reprojection (GAR) uses fine-tuned VGGT to reconstruct colored point clouds and reproject them to observed and virtual target poses, producing geometric condition maps. This design unifies the reprojection path between training and inference. Artifact-Guided Latent Diffusion (AGLD) injects reprojection-derived artifact masks during training so the model learns to recover structure under missing support. For evaluation, we use a LiDAR-Projected Sparse-Reference (LPSR) protocol when dense extrapolated-view ground truth is unavailable. On Waymo, Geo-EVS improves sparse-view synthesis quality and geometric accuracy, especially in high-angle and low-coverage settings. It also improves downstream 3D detection.
format Preprint
id arxiv_https___arxiv_org_abs_2604_07250
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Geo-EVS: Geometry-Conditioned Extrapolative View Synthesis for Autonomous Driving
Lan, Yatong
Tang, Rongkui
He, Lei
Computer Vision and Pattern Recognition
Extrapolative novel view synthesis can reduce camera-rig dependency in autonomous driving by generating standardized virtual views from heterogeneous sensors. Existing methods degrade outside recorded trajectories because extrapolated poses provide weak geometric support and no dense target-view supervision. The key is to explicitly expose the model to out-of-trajectory condition defects during training. We propose Geo-EVS, a geometry-conditioned framework under sparse supervision. Geo-EVS has two components. Geometry-Aware Reprojection (GAR) uses fine-tuned VGGT to reconstruct colored point clouds and reproject them to observed and virtual target poses, producing geometric condition maps. This design unifies the reprojection path between training and inference. Artifact-Guided Latent Diffusion (AGLD) injects reprojection-derived artifact masks during training so the model learns to recover structure under missing support. For evaluation, we use a LiDAR-Projected Sparse-Reference (LPSR) protocol when dense extrapolated-view ground truth is unavailable. On Waymo, Geo-EVS improves sparse-view synthesis quality and geometric accuracy, especially in high-angle and low-coverage settings. It also improves downstream 3D detection.
title Geo-EVS: Geometry-Conditioned Extrapolative View Synthesis for Autonomous Driving
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2604.07250