33 citations · 253 across the 23 of their papers we have counts for
25 papers
Less is More: Consistent Video Depth Estimation with Masked Frames Modeling
Yiran Wang, Zhiyu Pan, Xingyi Li +3
Temporal consistency is the key challenge of video depth estimation. Previous works are based on additional optical flow or camera poses, which is time-consuming. By contrast, we d…
DoF-NeRF: Depth-of-Field Meets Neural Radiance Fields
Zijin Wu, Xingyi Li, Juewen Peng +3
Neural Radiance Field (NeRF) and its variants have exhibited great success on representing 3D scenes and synthesizing photo-realistic novel views. However, they are generally based…
MPIB: An MPI-Based Bokeh Rendering Framework for Realistic Partial Occlusion Effects
Juewen Peng, Jianming Zhang, Xianrui Luo +3
Partial occlusion effects are a phenomenon that blurry objects near a camera are semi-transparent, resulting in partial appearance of occluded background. However, it is challengin…
BokehMe: When Neural Rendering Meets Classical Rendering
Juewen Peng, Zhiguo Cao, Xianrui Luo +3
We propose BokehMe, a hybrid bokeh rendering framework that marries a neural renderer with a classical physically motivated renderer. Given a single image and a potentially imperfe…
Represent, Compare, and Learn: A Similarity-Aware Framework for Class-Agnostic Counting
Min Shi, Hao Lu, Chen Feng +2
Class-agnostic counting (CAC) aims to count all instances in a query image given few exemplars. A standard pipeline is to extract visual features from exemplars and match them with…
Fast and Accurate Single-Image Depth Estimation on Mobile Devices, Mobile AI 2021 Challenge: Report
Andrey Ignatov, Grigory Malivenko, David Plowman +35
Depth estimation is an important computer vision problem with many practical applications to mobile devices. While many solutions have been proposed for this task, they are usually…
AIM 2020 Challenge on Rendering Realistic Bokeh
Andrey Ignatov, Radu Timofte, Ming Qian +32
This paper reviews the second AIM realistic bokeh effect rendering challenge and provides the description of the proposed solutions and results. The participating teams were solvin…
Weighing Counts: Sequential Crowd Counting by Reinforcement Learning
Liang Liu, Hao Lu, Hongwei Zou +3
We formulate counting as a sequential decision problem and present a novel crowd counting model solvable by deep reinforcement learning. In contrast to existing counting models tha…
P2B: Point-to-Box Network for 3D Object Tracking in Point Clouds
Haozhe Qi, Chen Feng, Zhiguo Cao +2
Towards 3D object tracking in point clouds, a novel point-to-box network termed P2B is proposed in an end-to-end learning manner. Our main idea is to first localize potential targe…
3DV: 3D Dynamic Voxel for Action Recognition in Depth Video
Yancheng Wang, Yang Xiao, Fu Xiong +4
To facilitate depth-based 3D action recognition, 3D dynamic voxel (3DV) is proposed as a novel 3D motion representation. With 3D space voxelization, the key idea of 3DV is to encod…
Measuring Generalisation to Unseen Viewpoints, Articulations, Shapes and Objects for 3D Hand Pose Estimation under Hand-Object Interaction
Anil Armagan, Guillermo Garcia-Hernando, Seungryul Baek +32
We study how well different types of approaches generalise in the task of 3D hand pose estimation under single hand scenarios and hand-object interaction. We show that the accuracy…
LRF-Net: Learning Local Reference Frames for 3D Local Shape Description and Matching
Angfan Zhu, Jiaqi Yang, Weiyue Zhao +1
The local reference frame (LRF) acts as a critical role in 3D local shape description and matching. However, most of existing LRFs are hand-crafted and suffer from limited repeatab…
Rotation Invariant Point Cloud Classification: Where Local Geometry Meets Global Topology
Chen Zhao, Jiaqi Yang, Xin Xiong +3
Point cloud analysis is a fundamental task in 3D computer vision. Most previous works have conducted experiments on synthetic datasets with well-aligned data; while real-world poin…
A2J: Anchor-to-Joint Regression Network for 3D Articulated Pose Estimation from a Single Depth Image
Fu Xiong, Boshen Zhang, Yang Xiao +4
For 3D hand and body pose estimation task in depth image, a novel anchor-based approach termed Anchor-to-Joint regression network (A2J) with the end-to-end learning ability is prop…
From Open Set to Closed Set: Counting Objects by Spatial Divide-and-Conquer
Haipeng Xiong, Hao Lu, Chengxin Liu +3
Visual counting, a task that predicts the number of objects from an image/video, is an open-set problem by nature, i.e., the number of population can vary in in theor…
Learning to Fuse Local Geometric Features for 3D Rigid Data Matching
Jiaqi Yang, Chen Zhao, Ke Xian +2
This paper presents a simple yet very effective data-driven approach to fuse both low-level and high-level local geometric features for 3D rigid data matching. It is a common pract…
NM-Net: Mining Reliable Neighbors for Robust Feature Correspondences
Chen Zhao, Zhiguo Cao, Chi Li +2
Feature correspondence selection is pivotal to many feature-matching based tasks in computer vision. Searching for spatially k-nearest neighbors is a common strategy for extracting…
Towards Real-time Eyeblink Detection in The Wild:Dataset,Theory and Practices
Guilei Hu, Yang Xiao, Zhiguo Cao +4
Effective and real-time eyeblink detection is of wide-range applications, such as deception detection, drive fatigue detection, face anti-spoofing, etc. Although numerous of effort…
Towards Good Practices on Building Effective CNN Baseline Model for Person Re-identification
Fu Xiong, Yang Xiao, Zhiguo Cao +3
Person re-identification is indeed a challenging visual recognition task due to the critical issues of human pose variation, human body occlusion, camera view variation, etc. To ad…
Deep attention-based classification network for robust depth prediction
Ruibo Li, Ke Xian, Chunhua Shen +3
In this paper, we present our deep attention-based classification (DABC) network for robust single image depth prediction, in the context of the Robust Vision Challenge 2018 (ROB 2…
Action Recognition for Depth Video using Multi-view Dynamic Images
Yang Xiao, Jun Chen, Yancheng Wang +3
Dynamic imaging is a recently proposed action description paradigm for simultaneously capturing motion and temporal evolution information, particularly in the context of deep convo…
Monocular Depth Estimation with Augmented Ordinal Depth Relationships
Yuanzhouhan Cao, Tianqi Zhao, Ke Xian +3
Most existing algorithms for depth estimation from single monocular images need large quantities of metric groundtruth depths for supervised learning. We show that relative depth c…
Performance Evaluation of 3D Correspondence Grouping Algorithms
Jiaqi Yang, Ke Xian, Yang Xiao +1
This paper presents a thorough evaluation of several widely-used 3D correspondence grouping algorithms, motived by their significance in vision tasks relying on correct feature cor…
When Unsupervised Domain Adaptation Meets Tensor Representations
Hao Lu, Lei Zhang, Zhiguo Cao +4
Domain adaption (DA) allows machine learning methods trained on data sampled from one distribution to be applied to data sampled from another. It is thus of great practical importa…