19 citations · 74 across the 35 of their papers we have counts for
36 papers
MeanSR: Restoration Trajectory Learning for One-Step Perceptual Super-Resolution
Axi Niu, Jiawei Kou, Kang Zhang +3
Diffusion-based super-resolution (SR) achieves strong perceptual quality but requires costly iterative denoising. Existing one-step distillation methods reduce inference time but d…
Coupled Continuous-Discrete Generation for Scene Text Image Super-Resolution
Axi Niu, Knag Zhang, Qingsen Yan +3
Scene text image super-resolution (STISR) aims to recover visually plausible appearance while preserving character semantics from degraded inputs. Existing STISR systems often rely…
FaithIR: Rethinking Infrared Image Super-Resolution from Perceptual Sharpness to Task Relevant Fidelity
Axi Niu, Zhenguo Wu, Kang Zhang +3
Infrared image super-resolution (IISR) is important for downstream tasks such as object detection and semantic segmentation. Existing IISR methods often produce artificial textures…
Unleashing the Power of Text: Text-Guided Flow Matching for Image Fusion under Complex Degradations
Axi Niu, Jieheng Li, Kang Zhang +3
Infrared-visible image fusion under realistic degradation scenarios is a challenging task, as degradations not only cause a loss of reliable modality-specific information in observ…
The Second Challenge on Real-World Face Restoration at NTIRE 2026: Methods and Results
Jingkai Wang, Jue Gong, Zheng Chen +50
This paper provides a review of the NTIRE 2026 challenge on real-world face restoration, highlighting the proposed solutions and the resulting outcomes. The challenge focuses on ge…
DualTSR: Unified Dual-Diffusion Transformer for Scene Text Image Super-Resolution
Axi Niu, Kang Zhang, Qingsen Yan +3
Scene Text Image Super-Resolution (STISR) aims to restore high-resolution details in low-resolution text images, which is crucial for both human readability and machine recognition…
PoseCrafter: Extreme Pose Estimation with Hybrid Video Synthesis
Qing Mao, Tianxin Huang, Yu Zhu +3
Pairwise camera pose estimation from sparsely overlapping image pairs remains a critical and unsolved challenge in 3D vision. Most existing methods struggle with image pairs that h…
Sparse2DGS: Geometry-Prioritized Gaussian Splatting for Surface Reconstruction from Sparse Views
Jiang Wu, Rui Li, Yu Zhu +3
We present a Gaussian Splatting method for surface reconstruction using sparse input views. Previous methods relying on dense views struggle with extremely sparse Structure-from-Mo…
Boosting HDR Image Reconstruction via Semantic Knowledge Transfer
Tao Hu, Longyao Wu, Wei Dong +5
Recovering High Dynamic Range (HDR) images from multiple Standard Dynamic Range (SDR) images become challenging when the SDR images exhibit noticeable degradation and missing conte…
HVI: A New Color Space for Low-light Image Enhancement
Qingsen Yan, Yixu Feng, Cheng Zhang +6
Low-Light Image Enhancement (LLIE) is a crucial computer vision task that aims to restore detailed visual information from corrupted low-light images. Many existing LLIE methods ar…
C-Drag: Chain-of-Thought Driven Motion Controller for Video Generation
Yuhao Li, Mirana Claire Angel, Salman Khan +4
Trajectory-based motion control has emerged as an intuitive and efficient approach for controllable video generation. However, the existing trajectory-based approaches are usually…
UIR-LoRA: Achieving Universal Image Restoration through Multiple Low-Rank Adaptation
Cheng Zhang, Dong Gong, Jiumei He +3
Existing unified methods typically treat multi-degradation image restoration as a multi-task learning problem. Despite performing effectively compared to single degradation restora…
Multi-Granularity Language-Guided Training for Multi-Object Tracking
Yuhao Li, Jiale Cao, Muzammal Naseer +4
Most existing multi-object tracking methods typically learn visual tracking features via maximizing dis-similarities of different instances and minimizing similarities of the same…
The Third Monocular Depth Estimation Challenge
Jaime Spencer, Fabio Tosi, Matteo Poggi +38
This paper discusses the results of the third edition of the Monocular Depth Estimation Challenge (MDEC). The challenge focuses on zero-shot generalization to the challenging SYNS-…
NTIRE 2024 Challenge on Low Light Image Enhancement: Methods and Results
Xiaoning Liu, Zongwei Wu, Ao Li +109
This paper reviews the NTIRE 2024 low light image enhancement challenge, highlighting the proposed solutions and results. The aim of this challenge is to discover an effective netw…
GoMVS: Geometrically Consistent Cost Aggregation for Multi-View Stereo
Jiang Wu, Rui Li, Haofei Xu +4
Matching cost aggregation plays a fundamental role in learning-based multi-view stereo networks. However, directly aggregating adjacent costs can lead to suboptimal results due to…
You Only Need One Color Space: An Efficient Network for Low-light Image Enhancement
Qingsen Yan, Yixu Feng, Cheng Zhang +5
Low-Light Image Enhancement (LLIE) task tends to restore the details and visual information from corrupted low-light images. Most existing methods learn the mapping function betwee…
Boosting Multi-view Stereo with Late Cost Aggregation
Jiang Wu, Rui Li, Yu Zhu +3
Pairwise matching cost aggregation is a crucial step for modern learning-based Multi-view Stereo (MVS). Prior works adopt an early aggregation scheme, which adds up pairwise costs…
DifAugGAN: A Practical Diffusion-style Data Augmentation for GAN-based Single Image Super-resolution
Axi Niu, Kang Zhang, Joshua Tian Jin Tee +5
It is well known the adversarial optimization of GAN-based image super-resolution (SR) methods makes the preceding SR model generate unpleasant and undesirable artifacts, leading t…
Multiple Object Tracking based on Occlusion-Aware Embedding Consistency Learning
Yaoqi Hu, Axi Niu, Yu Zhu +3
The Joint Detection and Embedding (JDE) framework has achieved remarkable progress for multiple object tracking. Existing methods often employ extracted embeddings to re-establish…
All-in-one Multi-degradation Image Restoration Network via Hierarchical Degradation Representation
Cheng Zhang, Yu Zhu, Qingsen Yan +2
The aim of image restoration is to recover high-quality images from distorted ones. However, current methods usually focus on a single task (\emph{e.g.}, denoising, deblurring or s…
ACDMSR: Accelerated Conditional Diffusion Models for Single Image Super-Resolution
Axi Niu, Pham Xuan Trung, Kang Zhang +4
Diffusion models have gained significant popularity in the field of image-to-image translation. Previous efforts applying diffusion models to image super-resolution (SR) have demon…
Learning from Multi-Perception Features for Real-Word Image Super-resolution
Axi Niu, Kang Zhang, Trung X. Pham +4
Currently, there are two popular approaches for addressing real-world image super-resolution problems: degradation-estimation-based and blind-based methods. However, degradation-es…
Learning to Fuse Monocular and Multi-view Cues for Multi-frame Depth Estimation in Dynamic Scenes
Rui Li, Dong Gong, Wei Yin +6
Multi-frame depth estimation generally achieves high accuracy relying on the multi-view geometric consistency. When applied in dynamic scenes, e.g., autonomous driving, this consis…