activity
20192022
most citedDFANet: Deep Feature Aggregation for Real-Time Semantic Segmentation

57 citations · 130 across the 17 of their papers we have counts for

collaborators

24 papers

eess.IV2022

Efficient and Accurate Quantized Image Super-Resolution on Mobile NPUs, Mobile AI & AIM 2022 challenge: Report

Andrey Ignatov, Radu Timofte, Maurizio Denna +93

Image super-resolution is a common task on mobile and IoT devices, where one often needs to upscale and enhance low-resolution images and video frames. While numerous solutions hav…

cs.CV202211 cited

NTIRE 2022 Challenge on High Dynamic Range Imaging: Methods and Results

Eduardo Pérez-Pellitero, Sibi Catley-Chandar, Richard Shaw +85

This paper reviews the challenge on constrained high dynamic range (HDR) imaging that was part of the New Trends in Image Restoration and Enhancement (NTIRE) workshop, held in conj…

cs.CV2022

NTIRE 2022 Challenge on Efficient Super-Resolution: Methods and Results

Yawei Li, Kai Zhang, Radu Timofte +108

This paper reviews the NTIRE 2022 challenge on efficient single image super-resolution with focus on the proposed solutions and results. The task of the challenge was to super-reso…

cs.CV2022

BSRT: Improving Burst Super-Resolution with Swin Transformer and Flow-Guided Deformable Alignment

Ziwei Luo, Youwei Li, Shen Cheng +6

This work addresses the Burst Super-Resolution (BurstSR) task using a new architecture, which requires restoring a high-quality image from a sequence of noisy, misaligned, and low-…

cs.CV20229 cited

Towards Self-Supervised Category-Level Object Pose and Size Estimation

Yisheng He, Haoqiang Fan, Haibin Huang +2

In this work, we tackle the challenging problem of category-level object pose and size estimation from a single depth image. Although previous fully-supervised works have demonstra…

cs.CV20222 cited

FS6D: Few-Shot 6D Pose Estimation of Novel Objects

Yisheng He, Yao Wang, Haoqiang Fan +2

6D object pose estimation networks are limited in their capability to scale to large numbers of object instances due to the close-set assumption and their reliance on high-fidelity…