activity
20182022
most citedNerfingMVS: Guided Optimization of Neural Radiance Fields for Indoor Multi-view Stereo

11 citations · 23 across the 5 of their papers we have counts for

collaborators
Showing cs.CVShow all

6 papers · 1 filter

cs.CV202111 cited

NerfingMVS: Guided Optimization of Neural Radiance Fields for Indoor Multi-view Stereo

Yi Wei, Shaohui Liu, Yongming Rao +3

In this work, we present a new multi-view depth estimation method that utilizes both conventional reconstruction and learning-based priors over the recently proposed neural radianc…

cs.CV2021

RandomRooms: Unsupervised Pre-training from Synthetic Shapes and Randomized Layouts for 3D Object Detection

Yongming Rao, Benlin Liu, Yi Wei +3

3D point cloud understanding has made great progress in recent years. However, one major bottleneck is the scarcity of annotated real datasets, especially compared to 2D object det…

cs.CV20212 cited

FGR: Frustum-Aware Geometric Reasoning for Weakly Supervised 3D Vehicle Detection

Yi Wei, Shang Su, Jiwen Lu +1

In this paper, we investigate the problem of weakly supervised 3D vehicle detection. Conventional methods for 3D object detection need vast amounts of manually labelled 3D data as…

cs.CV2020

PV-RAFT: Point-Voxel Correlation Fields for Scene Flow Estimation of Point Clouds

Yi Wei, Ziyi Wang, Yongming Rao +2

In this paper, we propose a Point-Voxel Recurrent All-Pairs Field Transforms (PV-RAFT) method to estimate scene flow from point clouds. Since point clouds are irregular and unorder…

cs.CV201910 cited

Conditional Single-view Shape Generation for Multi-view Stereo Reconstruction

Yi Wei, Shaohui Liu, Wang Zhao +2

In this paper, we present a new perspective towards image-based shape generation. Most existing deep learning based shape reconstruction methods employ a single-view deterministic…

cs.CV2018

An Improved Evaluation Framework for Generative Adversarial Networks

Shaohui Liu, Yi Wei, Jiwen Lu +1

In this paper, we propose an improved quantitative evaluation framework for Generative Adversarial Networks (GANs) on generating domain-specific images, where we improve convention…