Zihao Huang

22 papers · 2023–2026 · 8 conferences · across top CS/AI conferences

Achievements

🌈 Renaissance Researcher (7) 🌍 Conference Polyglot (7) 🐝 Cross-Pollinator (5) 🗺️ Taxonomy Completionist (50) 🧭 Keyword Pioneer 🌉 Interdisciplinary Bridge 🏆 Keyword Champion (3) 🏆 Grand Slam 🤝 Dynamic Duo (10) 🗃️ Keyword Collector (90) 💎 Century Club (16) ⚡ Prolific Year (11)

Conferences

AAAI (6) ICCV (6) CVPR (3) COLING (2) ICLR (2) ACL (1) ICML (1) NIPS (1)

Top co-authors

Zhiguo Cao (10) Tianqi Liu (6) Jiaqi Li (5) Huiqiang Sun (4) Liao Shen (4) Bohan Fu (3) Yang Gu (3) Min Shi (3) Defa Zhu (3) Fazhan Zhang (3)

Research topics

Keywords

depth estimation (4) grammatical error correction (3) error annotation (3) 3d reconstruction (3) multilingual nlp (2) point cloud quality assessment (2) temporal consistency (2) multi-view stereo (2) bokeh rendering (2) vision-language model (2) depth refinement (2) novel view synthesis (2) text annotation (1) transfer learning (1) optimal transport (1) self-attention mechanism (1) video generation (1) prompt learning (1) natural language processing (1) few-shot learning (1)

Papers

BokehFlow: Depth-Free Controllable Bokeh Rendering via Flow Matching AAAI 2026

Points Meet Pixels: Bridging 2D Vision-Language Model and 3D Perception Gaps for Point Cloud Quality Assessment AAAI 2026

DSP-PCQA: Integrating Multiple Perception Preferences for Point Cloud Quality Assessment AAAI 2026

BokehCrafter: Taming Video Diffusion Models for Controllable Bokeh Rendering AAAI 2026

LLM-CAS: Dynamic Neuron Perturbation for Real-Time Hallucination Correction AAAI 2026

DR.Experts: Differential Refinement of Distortion-Aware Experts for Blind Image Quality Assessment AAAI 2026

MuGS: Multi-Baseline Generalizable Gaussian Splatting Reconstruction ICCV 2025

Unsupervised Histopathological Image Semantic Segmentation with Overlapping Patches Consistency Constraint ICCV 2025

Ultra-Sparse Memory Network ICLR 2025

Hyper-Connections ICLR 2025

Expert Race: A Flexible Routing Strategy for Scaling Diffusion Transformer with Mixture of Experts ICML 2025

Few-Shot Image Quality Assessment via Adaptation of Vision-Language Models ICCV 2025

Multilingual Grammatical Error Annotation: Combining Language-Agnostic Framework with Language-Specific Flexibility ACL 2025

Refined Evaluation for End-to-End Grammatical Error Correction Using an Alignment-Based Approach COLING 2025

Improving Automatic Grammatical Error Annotation for Chinese Through Linguistically-Informed Error Typology COLING 2025

WildAvatar: Learning In-the-wild 3D Avatars from the Web CVPR 2025

Free4D: Tuning-free 4D Scene Generation with Spatial-Temporal Consistency ICCV 2025

Self-Distilled Depth Refinement with Noisy Poisson Fusion NIPS 2024

Geometry-aware Reconstruction and Fusion-refined Rendering for Generalizable Neural Radiance Fields CVPR 2024

Constraining Depth Map Geometry for Multi-View Stereo: A Dual-Depth Approach with Saddle-shaped Depth Cells ICCV 2023

Neural Video Depth Stabilizer ICCV 2023

Matching Is Not Enough: A Two-Stage Framework for Category-Agnostic Pose Estimation CVPR 2023