Learning to fuse monocular and multi-view cues for multi-frame depth estimation in dynamic scenes

R Li, D Gong, W Yin, H Chen, Y Zhu… - Proceedings of the …, 2023 - openaccess.thecvf.com
Multi-frame depth estimation generally achieves high accuracy relying on the multi-view
geometric consistency. When applied in dynamic scenes, eg, autonomous driving, this …

Digging into depth priors for outdoor neural radiance fields

C Wang, J Sun, L Liu, C Wu, Z Shen, D Wu… - Proceedings of the 31st …, 2023 - dl.acm.org
Neural Radiance Fields (NeRFs) have demonstrated impressive performance in vision and
graphics tasks, such as novel view synthesis and immersive reality. However, the shape …

Know Your Neighbors: Improving Single-View Reconstruction via Spatial Vision-Language Reasoning

R Li, T Fischer, M Segu, M Pollefeys… - Proceedings of the …, 2024 - openaccess.thecvf.com
Recovering the 3D scene geometry from a single view is a fundamental yet ill-posed
problem in computer vision. While classical depth estimation methods infer only a 2.5 D …

SENSE: Self-Evolving Learning for Self-Supervised Monocular Depth Estimation

G Li, R Huang, H Li, Z You… - IEEE Transactions on …, 2023 - ieeexplore.ieee.org
Self-supervised depth estimation methods can achieve competitive performance using only
unlabeled monocular videos, but they suffer from the uncertainty of jointly learning depth …

Self-supervised monocular depth estimation with frequency-based recurrent refinement

R Li, D Xue, Y Zhu, H Wu, J Sun… - IEEE Transactions on …, 2022 - ieeexplore.ieee.org
Self-supervised monocular depth estimation has succeeded in learning scene geometry
from only image pairs or sequences. However, it is still highly ill-posed for self-supervised …

Learning depth via leveraging semantics: Self-supervised monocular depth estimation with both implicit and explicit semantic guidance

R Li, D Xue, S Su, X He, Q Mao, Y Zhu, J Sun… - Pattern Recognition, 2023 - Elsevier
Self-supervised monocular depth estimation has shown great success in learning depth
using only images for supervision. In this paper, we propose to enhance self-supervised …

Frequency-aware self-supervised monocular depth estimation

X Chen, TH Li, R Zhang, G Li - Proceedings of the IEEE …, 2023 - openaccess.thecvf.com
We present two versatile methods to generally enhance self-supervised monocular depth
estimation (MDE) models. The high generalizability of our methods is achieved by solving …

Non-uniform motion deblurring with blurry component divided guidance

P Wang, W Sun, Q Yan, A Niu, R Li, Y Zhu, J Sun… - Pattern Recognition, 2021 - Elsevier
Blind image deblurring is a fundamental and challenging computer vision problem, which
aims to recover both the blur kernel and the latent sharp image from only a blurry …

GRAN: ghost residual attention network for single image super resolution

A Niu, P Wang, Y Zhu, J Sun, Q Yan… - Multimedia Tools and …, 2024 - Springer
Recently, many works have designed wider and deeper networks to achieve higher image
super-resolution performance. Despite their outstanding performance, they still suffer from …

SM4Depth: Seamless Monocular Metric Depth Estimation across Multiple Cameras and Scenes by One Model

Y Liu, F Xue, A Ming, M Zhao, H Ma, N Sebe - arXiv preprint arXiv …, 2024 - arxiv.org
In the last year, universal monocular metric depth estimation (universal MMDE) has gained
considerable attention, serving as the foundation model for various multimedia tasks, such …