Zhiwei Xiong

69

Papers

72

Total Citations

Papers (69)

Distilling Semantic Priors from SAM to Efficient Image Restoration Models

Event-Adapted Video Super-Resolution

Fine-Grained Evaluation of Large Vision-Language Models in Autonomous Driving

TokenUnify: Scaling Up Autoregressive Pretraining for Neuron Segmentation

Exploiting Dual-Correlation for Multi-frame Time-of-Flight Denoising

Generalizable Non-Line-of-Sight Imaging with Learnable Physical Priors

Event-Enhanced Blurry Video Super-Resolution

Test-Time Adaptation via Style and Structure Guidance for Histological Image Registration

Learning Multimodal Volumetric Features for Large-Scale Neuron Tracing

Cross-Dimension Affinity Distillation for 3D EM Neuron Segmentation

Event-assisted Low-Light Video Object Segmentation

Learning Large-Factor EM Image Super-Resolution with Generative Priors

Look-Up Table Compression for Efficient Image Restoration

Towards Generalizable Tumor Synthesis

High-Speed Hyperspectral Video Acquisition With a Dual-Camera Architecture

Snapshot Hyperspectral Light Field Imaging

Camera Lens Super-Resolution

SPM-Tracker: Series-Parallel Matching for Real-Time Visual Object Tracking

Compact Feature Learning for Multi-Domain Image Classification

Camera Trace Erasing

Tracking by Instance Detection: A Meta-Learning Approach

Deep Degradation Prior for Low-Quality Image Classification

Light Field Super-Resolution With Zero-Shot Learning

Space-Time Distillation for Video Super-Resolution

Unsupervised Visual Representation Learning by Tracking Patches in Video

Recurrent Dynamic Embedding for Video Object Segmentation

Contextual Outpainting With Object-Level Contrastive Learning

Quantization-Aware Deep Optics for Diffractive Snapshot Hyperspectral Imaging

Exploiting Rigidity Constraints for LiDAR Scene Flow Estimation

Degradation-Agnostic Correspondence From Resolution-Asymmetric Stereo

Exposure Normalization and Compensation for Multiple-Exposure Correction

Style Projected Clustering for Domain Generalized Semantic Segmentation

Camouflaged Instance Segmentation via Explicit De-Camouflaging

CutMIB: Boosting Light Field Super-Resolution via Multi-View Image Blending

Depth Estimation From Indoor Panoramas With Neural Scene Representation

Progressive Spatio-Temporal Alignment for Efficient Event-Based Motion Estimation

Learning Sample Relationship for Exposure Correction

Learning Steerable Function for Efficient Image Resampling

Hierarchical Prompt Learning for Multi-Task Learning

A Soma Segmentation Benchmark in Full Adult Fly Brain

Toward RAW Object Detection: A New Benchmark and a New Model

Why Is the Winner the Best?

NLOST: Non-Line-of-Sight Imaging With Transformer

Event-Based Blurry Frame Interpolation Under Blind Exposure

DualRel: Semi-Supervised Mitochondria Segmentation From a Prototype Perspective

Zero-Shot Dual-Lens Super-Resolution

Plug-and-Play Versatile Compressed Video Enhancement

Event-Based Video Reconstruction Using Transformer

Unsupervised Video Deraining with An Event Camera

Generalized Lightness Adaptation with Channel Selective Normalization

GET: Group Event Transformer for Event-Based Vision

Learning Cross-Representation Affinity Consistency for Sparsely Supervised Biomedical Instance Segmentation

Adaptive Template Transformer for Mitochondria Segmentation in Electron Microscopy Images

Photon-Efficient 3D Imaging with A Non-Local Neural Network

Spatial Hierarchy Aware Residual Pyramid Network for Time-of-Flight Depth Denoising

Boosting Event Stream Super-Resolution with a Recurrent Neural Network

MuLUT: Cooperating Multiple Look-Up Tables for Efficient Image Super-Resolution

Deep Fourier-Based Exposure Correction Network with Spatial-Frequency Interaction

Towards Real-World HDRTV Reconstruction: A Data Synthesis-Based Approach

Two-Stream Action Recognition-Oriented Video Super-Resolution

S2D-LFE: Sparse-to-Dense Light Field Event Generation

TAR3D: Creating High-Quality 3D Assets via Next-Part Prediction

HDR Image Generation via Gain Map Decomposed Diffusion

GenFlow3D: Generative Scene Flow Estimation and Prediction on Point Cloud Sequences

Event-boosted Deformable 3D Gaussians for Dynamic Scene Reconstruction

On The Classification-Distortion-Perception Tradeoff

Unfolding Taylor's Approximations for Image Restoration

Transition-constant Normalization for Image Enhancement

Deep Non-line-of-sight Imaging from Under-scanning Measurements