Nerfbusters: Removing ghostly artifacts from casually captured nerfs

F Warburg, E Weber, M Tancik… - Proceedings of the …, 2023 - openaccess.thecvf.com
Abstract Casually captured Neural Radiance Fields (NeRFs) suffer from artifacts such as
floaters or flawed geometry when rendered outside the input camera trajectory. Existing …

Flexible Depth Completion for Sparse and Varying Point Densities

J Park, YJ Li, K Kitani - … of the IEEE/CVF Conference on …, 2024 - openaccess.thecvf.com
While recent depth completion methods have achieved remarkable results filling in relatively
dense depth maps (eg projected 64-line LiDAR on KITTI or 500 sampled points on NYUv2) …

Deep sparse depth completion using multi-affinity matrix

W Zhao, C Jung, J Kim - IEEE Access, 2023 - ieeexplore.ieee.org
Image-guided depth completion aims to generate dense depth maps from sparse depth
maps guided by their corresponding color (RGB) images. In this paper, we propose deep …

Depth completion with multiple balanced bases and confidence for dense monocular slam

W **e, G Chu, Q Qian, Y Yu, H Li… - … on Visualization and …, 2024 - ieeexplore.ieee.org
Dense SLAM based on monocular cameras does indeed have immense application value in
the field of AR/VR, especially when it is performed on a mobile device. In this paper, we …

Sparse Depth Completion Based on Boundary Prediction Assistance

H ZHOU, T LI, M SUN, D WU, M ZHOU - Journal of **hua University …, 2025 - xhuqk.com
Depth images completion aims to recover dense depth images from sparse depth images,
however, the depth images restored by many current depth completion algorithms often …

[PDF][PDF] Flexible Depth Completion for Sparse and Varying Point Densities (Supplementary Material)

J Park, YJLK Kitani - openaccess.thecvf.com
• Section G presents a comparison of our method to Sparsity Agnostic Depth Completion [5].•
Section I contains additional details of the nuScenes depth completion dataset as well as …

基于边界预测辅助的稀疏深度修复

周恒, **滔, 孙明明, 武丹丹, 周明会 - 西华大学学报 (自然科学版), 2025 - xhuqk.com
深度图像修复旨在从稀疏深度图像中恢复出稠密的深度图像, 然而目前许多深度修复算法所修复
出的深度图像往往存在细节结构缺失, 深度不连续和边界模糊等问题. 针对这些问题 …