Haichuan Song

11 papers · 2020–2026 · 5 venues · across top CS/AI venues

Authors are matched by name, so researchers who share a name ("Yang Liu", "Wei Wang") appear as a single profile and their paper counts, venues and achievements are combined. How identity is handled.

Achievements

Jump to papers ↓

+1 more ↓

🌍 Conference Polyglot · Silver 🏃 Academic Marathon · Sprint 🌉 Interdisciplinary Bridge · Bronze 🗺️ Taxonomy Completionist (17) 🐣 Hot Topic Early Bird

💎 Century Club · Bronze

Venues

CVPR (4) AAAI (3) ECCV (2) ICCV (1) IJCAI (1)

Top co-authors

Lizhuang Ma (5) Yuan Xie (4) Faming Fang (3) Xin Tan (3) Jiachen Xu (2) Kanle Shi (2) Ran Yi (2) Zhizhong Zhang (2) Jingyu Gong (2) Ke-Yue Zhang (1)

Research topics

Computer Vision (7) Machine Learning (6) Analysis (6) Learning Types (4) Processing (3) Artificial Intelligence (2) Deep Learning (2) Core Methods (2) Learning Paradigms (2) Models (2) Application Areas (1)

Keywords

semi-supervised learning (2) depth estimation (2) domain adaptation (1) transfer learning (1) 3d vision (1) image restoration (1) video frame interpolation (1) anomaly detection (1) motion estimation (1) self-supervised learning (1) domain generalization (1) semantic segmentation (1) image reconstruction (1) synthetic data generation (1) surface reconstruction (1) mutual information (1) vector quantization (1) geometric optimization (1) receptive field (1) volume rendering (1)

Papers

αMatte4K & μMatting: Dataset and Model for Ultra-Micro Precision Alpha Video Matting CVPR 2026 A Geometric Perspective on Optimizing Vector Quantized Latent Diffusion Model for Image Restoration AAAI 2026 Towards Privacy-Protected Generalized Gaze Estimation Using Diffusion Models and Domain Stability Adaptation Framework AAAI 2026 Explicit Depth-Aware Blurry Video Frame Interpolation Guided by Differential Curves CVPR 2025 MOS: Modeling Object-Scene Associations in Generalized Category Discovery CVPR 2025 SparseRecon: Neural Implicit Surface Reconstruction from Sparse Views with Feature and Depth Consistencies ICCV 2025 Optimization over Disentangled Encoding: Unsupervised Cross-Domain Point Cloud Completion via Occlusion Factor Manipulation ECCV 2022 Task-Level Self-Supervision for Cross-Domain Few-Shot Learning AAAI 2022 Omni-Supervised Point Cloud Segmentation via Gradual Receptive Field Component Reasoning CVPR 2021 Face Anti-Spoofing via Disentangled Representation Learning ECCV 2020 Latent Regularized Generative Dual Adversarial Network For Abnormal Detection IJCAI 2020