226 citations · 590 across the 36 of their papers we have counts for
15 papers · 1 filter
Efficient Single-Image Depth Estimation on Mobile Devices, Mobile AI & AIM 2022 Challenge: Report
Andrey Ignatov, Grigory Malivenko, Radu Timofte +36
Various depth estimation models are now widely used on many mobile and IoT devices for image segmentation, bokeh effect rendering, object tracking and many other mobile tasks. Thus…
Multi-Camera Collaborative Depth Prediction via Consistent Structure Estimation
Jialei Xu, Xianming Liu, Yuanchao Bai +4
Depth map estimation from images is an important task in robotic systems. Existing methods can be categorized into two groups including multi-view stereo and monocular depth estima…
LiteDepth: Digging into Fast and Accurate Depth Estimation on Mobile Devices
Zhenyu Li, Zehui Chen, Jialei Xu +2
Monocular depth estimation is an essential task in the computer vision community. While tremendous successful methods have obtained excellent results, most of them are computationa…
Prototype-Anchored Learning for Learning with Imperfect Annotations
Xiong Zhou, Xianming Liu, Deming Zhai +3
The success of deep neural networks greatly relies on the availability of large amounts of high-quality annotated data, which however are difficult or expensive to obtain. The resu…
Learning Towards the Largest Margins
Xiong Zhou, Xianming Liu, Deming Zhai +3
One of the main challenges for feature representation in deep learning-based classification is the design of appropriate loss functions that exhibit strong discriminative power. Th…
Towards Model Generalization for Monocular 3D Object Detection
Zhenyu Li, Zehui Chen, Ang Li +4
Monocular 3D object detection (Mono3D) has achieved tremendous improvements with emerging large-scale autonomous driving datasets and the rapid development of deep learning techniq…
GLaMa: Joint Spatial and Frequency Loss for General Image Inpainting
Zeyu Lu, Junjun Jiang, Junqin Huang +2
The purpose of image inpainting is to recover scratches and damaged areas using context information from remaining parts. In recent years, thanks to the resurgence of convolutional…
ReSmooth: Detecting and Utilizing OOD Samples when Training with Data Augmentation
Chenyang Wang, Junjun Jiang, Xiong Zhou +1
Data augmentation (DA) is a widely used technique for enhancing the training of deep neural networks. Recent DA techniques which achieve state-of-the-art performance always meet th…
Unsupervised Domain Adaptation for Monocular 3D Object Detection via Self-Training
Zhenyu Li, Zehui Chen, Ang Li +4
Monocular 3D object detection (Mono3D) has achieved unprecedented success with the advent of deep learning techniques and emerging large-scale autonomous driving datasets. However,…
Self-Supervised Arbitrary-Scale Point Clouds Upsampling via Implicit Neural Representation
Wenbo Zhao, Xianming Liu, Zhiwei Zhong +4
Point clouds upsampling is a challenging issue to generate dense and uniform point clouds from the given sparse input. Most existing methods either take the end-to-end supervised l…
BinsFormer: Revisiting Adaptive Bins for Monocular Depth Estimation
Zhenyu Li, Xuyang Wang, Xianming Liu +1
Monocular depth estimation is a fundamental task in computer vision and has drawn increasing attention. Recently, some methods reformulate it as a classification-regression task to…
DepthFormer: Exploiting Long-Range Correlation and Local Information for Accurate Monocular Depth Estimation
Zhenyu Li, Zehui Chen, Xianming Liu +1
This paper aims to address the problem of supervised monocular depth estimation. We start with a meticulous pilot study to demonstrate that the long-range correlation is essential…
Shadows can be Dangerous: Stealthy and Effective Physical-world Adversarial Attack by Natural Phenomenon
Yiqi Zhong, Xianming Liu, Deming Zhai +2
Estimating the risk level of adversarial examples is essential for safely deploying machine learning models in the real world. One popular approach for physical-world attacks is to…
Exploiting the Potential of Datasets: A Data-Centric Approach for Model Robustness
Yiqi Zhong, Lei Wu, Xianming Liu +1
Robustness of deep neural networks (DNNs) to malicious perturbations is a hot topic in trustworthy AI. Existing techniques obtain robust models given fixed datasets, either by modi…
SimIPU: Simple 2D Image and 3D Point Cloud Unsupervised Pre-Training for Spatial-Aware Visual Representations
Zhenyu Li, Zehui Chen, Ang Li +6
Pre-training has become a standard paradigm in many computer vision tasks. However, most of the methods are generally designed on the RGB image domain. Due to the discrepancy betwe…