.png){kind=icon}
.png){kind=icon}
Return
UncNeRF: Uncovering Heavily Occluded Object With Multi-View Clues
.png){kind=icon}
PRE
AI
J
Q
Y
DOI：10.1109/tip.2026.3716400.png)
.png){kind=icon}
Original request for help.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
Neural Radiance Fields can achieve photo-realistic rendering results, but the occlusion in front of the target object is a common and extreme scenario in practice that cannot be neglected. The prevailing works attempt to remove the occlusions using external 2D visual priors, which are not constrained to provide 3D-consistent guidance for the specific scenarios. In this paper, we propose UncNeRF, which utilizes multi-view clues from captured defective images to uncover the heavily occluded object. Specifically, we provide additional multi-view complementary optimization supervisions using object-centric forward warping and enhance the target object reconstruction by sampling pseudo-training views and introducing external spatial-relation regularization. To evaluate the reconstruction performance of occluded objects, we present the challenging and diverse Heavy Occlusion Removal (HOR) dataset consisting of synthetic and real-world scenes, whose target objects to be reconstructed are heavily occluded. Experimental results show that our method achieves state-of-the-art performance in heavy occlusion removal compared to other methods.
Keywords:
Novel view synthesis
neural radiance field
occlusions
Journal
IF:
13.7
Papers:
1.0W
Citations:
8.4W
Organization
Cited Papers