activity
20182026
most citedSurfaceNet+: An End-to-end 3D Neural Network for Very Sparse Multi-view Stereopsis

34 citations · 49 across the 8 of their papers we have counts for

collaborators
Showing cs.CVShow all

8 papers · 1 filter

cs.CV2026

Engram-E2VID: Reference-Based Event-to-Video Reconstruction via Generative Activation of Appearance Engrams

Feiyu Ji, Xiang Li, Hao Ma +6

Reference-based event-to-video reconstruction aims to recover target RGB frames from a reference frame and the event stream captured over the reference-to-target interval. Although…

cs.CV2026

DirectFisheye-GS: Enabling Native Fisheye Input in Gaussian Splatting with Cross-View Joint Optimization

Zhengxian Yang, Fei Xie, Xutao Xue +5

3D Gaussian Splatting (3DGS) has enabled efficient 3D scene reconstruction from everyday images with real-time, high-fidelity rendering, greatly advancing VR/AR applications. Fishe…

cs.CV2022

Cross-Camera Deep Colorization

Yaping Zhao, Haitian Zheng, Mengqi Ji +1

In this paper, we consider the color-plus-mono dual-camera system and propose an end-to-end convolutional neural network to align and fuse images from it in an efficient and cost-e…

cs.CV2021

EFENet: Reference-based Video Super-Resolution with Enhanced Flow Estimation

Yaping Zhao, Mengqi Ji, Ruqi Huang +2

In this paper, we consider the problem of reference-based video super-resolution(RefVSR), i.e., how to utilize a high-resolution (HR) reference frame to super-resolve a low-resolut…

cs.CV2020

Zoom in to the details of human-centric videos

Guanghan Li, Yaping Zhao, Mengqi Ji +2

Presenting high-resolution (HR) human appearance is always critical for the human-centric videos. However, current imagery equipment can hardly capture HR details all the time. Exi…

cs.CV2020★ 34 cited

SurfaceNet+: An End-to-end 3D Neural Network for Very Sparse Multi-view Stereopsis

Mengqi Ji, Jinzhi Zhang, Qionghai Dai +1

Multi-view stereopsis (MVS) tries to recover the 3D model from 2D images. As the observations become sparser, the significant 3D information loss makes the MVS problem more challen…