Saved in:
Bibliographic Details
Main Authors: Lin, Liqiang, Wu, Wenpeng, Fu, Chi-Wing, Zhang, Hao, Huang, Hui
Format: Preprint
Published: 2024
Subjects:
Online Access:https://arxiv.org/abs/2412.01618
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866913594569916416
author Lin, Liqiang
Wu, Wenpeng
Fu, Chi-Wing
Zhang, Hao
Huang, Hui
author_facet Lin, Liqiang
Wu, Wenpeng
Fu, Chi-Wing
Zhang, Hao
Huang, Hui
contents We introduce camera ray matching (CRAYM) into the joint optimization of camera poses and neural fields from multi-view images. The optimized field, referred to as a feature volume, can be "probed" by the camera rays for novel view synthesis (NVS) and 3D geometry reconstruction. One key reason for matching camera rays, instead of pixels as in prior works, is that the camera rays can be parameterized by the feature volume to carry both geometric and photometric information. Multi-view consistencies involving the camera rays and scene rendering can be naturally integrated into the joint optimization and network training, to impose physically meaningful constraints to improve the final quality of both the geometric reconstruction and photorealistic rendering. We formulate our per-ray optimization and matched ray coherence by focusing on camera rays passing through keypoints in the input images to elevate both the efficiency and accuracy of scene correspondences. Accumulated ray features along the feature volume provide a means to discount the coherence constraint amid erroneous ray matching. We demonstrate the effectiveness of CRAYM for both NVS and geometry reconstruction, over dense- or sparse-view settings, with qualitative and quantitative comparisons to state-of-the-art alternatives.
format Preprint
id arxiv_https___arxiv_org_abs_2412_01618
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle CRAYM: Neural Field Optimization via Camera RAY Matching
Lin, Liqiang
Wu, Wenpeng
Fu, Chi-Wing
Zhang, Hao
Huang, Hui
Computer Vision and Pattern Recognition
Graphics
We introduce camera ray matching (CRAYM) into the joint optimization of camera poses and neural fields from multi-view images. The optimized field, referred to as a feature volume, can be "probed" by the camera rays for novel view synthesis (NVS) and 3D geometry reconstruction. One key reason for matching camera rays, instead of pixels as in prior works, is that the camera rays can be parameterized by the feature volume to carry both geometric and photometric information. Multi-view consistencies involving the camera rays and scene rendering can be naturally integrated into the joint optimization and network training, to impose physically meaningful constraints to improve the final quality of both the geometric reconstruction and photorealistic rendering. We formulate our per-ray optimization and matched ray coherence by focusing on camera rays passing through keypoints in the input images to elevate both the efficiency and accuracy of scene correspondences. Accumulated ray features along the feature volume provide a means to discount the coherence constraint amid erroneous ray matching. We demonstrate the effectiveness of CRAYM for both NVS and geometry reconstruction, over dense- or sparse-view settings, with qualitative and quantitative comparisons to state-of-the-art alternatives.
title CRAYM: Neural Field Optimization via Camera RAY Matching
topic Computer Vision and Pattern Recognition
Graphics
url https://arxiv.org/abs/2412.01618