Jiawei Zhang

39

Papers

412

Total Citations

Papers (39)

DNGaussian: Optimizing Sparse-View 3D Gaussian Radiance Fields with Global-Local Depth Normalization

EIA: ENVIRONMENTAL INJECTION ATTACK ON GENERALIST WEB AGENTS FOR PRIVACY LEAKAGE

GuardAgent: Safeguard LLM Agents via Knowledge-Enabled Reasoning

DiffRetouch: Using Diffusion to Retouch on the Shoulder of Experts

FaceSpeak: Expressive and High-Quality Speech Synthesis from Human Portraits of Different Styles

ChatScene: Knowledge-Enabled Safety-Critical Scenario Generation for Autonomous Vehicles

A Unified Linear Programming Framework for Offline Reward Learning from Human Demonstrations and Feedback

Uniformly Stable Algorithms for Adversarial Training and Beyond

Learning Fully Convolutional Networks for Iterative Non-Blind Deconvolution

Dynamic Scene Deblurring Using Spatially Variant Recurrent Neural Networks

Learning Dual Convolutional Neural Networks for Low-Level Vision

Gated Fusion Network for Single Image Dehazing

DAVANet: Stereo Deblurring With View Aggregation

Visually Imbalanced Stereo Matching

Learning a Reinforced Agent for Flexible Exposure Bracketing Selection

Learning a Non-Blind Deblurring Network for Night Blurry Images

Blind Deblurring for Saturated Images

RestoreFormer: High-Quality Blind Face Restoration From Undegraded Key-Value Pairs

Revisiting Domain Generalized Stereo Matching Networks From a Feature Consistency Perspective

CREST: Convolutional Residual Learning for Visual Tracking

Spatio-Temporal Filter Adaptive Network for Video Deblurring

Learning RAW-to-sRGB Mappings With Inaccurately Aligned Supervision

Deep Blind Video Super-Resolution

Learning To Know Where To See: A Visibility-Aware Approach for Occluded Person Re-Identification

Efficient Region-Aware Neural Radiance Fields for High-Fidelity Talking Portrait Synthesis

Learning Event-Driven Video Deblurring and Interpolation

OID: Outlier Identifying and Discarding in Blind Image Deblurring

EfficientFCN: Holistically-guided Decoding for Semantic Segmentation

InsTaG: Learning Personalized 3D Talking Head from Few-Second Video

FATE: Full-head Gaussian Avatar with Textural Editing from Monocular Video

TeRA: Rethinking Text-guided Realistic 3D Avatar Generation

A Diffusion-Based Framework for Occluded Object Movement

Robust Synthetic-to-Real Transfer for Stereo Matching

Deep Non-Blind Deconvolution via Generalized Low-Rank Approximation

Cross-Scale Internal Graph Neural Network for Image Super-Resolution

A Single-Loop Smoothed Gradient Descent-Ascent Algorithm for Nonconvex-Concave Min-Max Problems

When Expressivity Meets Trainability: Fewer than $n$ Neurons Can Work

Improving Certified Robustness via Statistical Learning with Logical Reasoning

What is a Good Metric to Study Generalization of Minimax Learners?