Siyu Zhu

CrowdGaussian: Reconstructing High-Fidelity 3D Gaussians for Human Crowd from a Single Image CVPR 2026 Head-wise Adaptive Rotary Positional Encoding for Fine-Grained Image Generation CVPR 2026 MixFlow Training: Alleviating Exposure Bias with Slowed Interpolation Mixture CVPR 2026 T⋆: Progressive Block Scaling for Masked Diffusion Language Models Through Trajectory Aware Reinforcement Learning ACL 2026 WAM-Flow: Parallel Coarse-to-Fine Motion Planning via Discrete Flow Matching for Autonomous Driving CVPR 2026 4D Diffusion for Dynamic Protein Structure Prediction with Reference and Motion Guidance AAAI 2025 AlphaPO: Reward Shape Matters for LLM Alignment ICML 2025 Dirichlet-Constrained Variational Codebook Learning for Temporally Coherent Video Face Restoration ICCV 2025 Flow Distillation Sampling: Regularizing 3D Gaussians with Pre-trained Matching Priors ICLR 2025 Hallo2: Long-Duration and High-Resolution Audio-Driven Portrait Image Animation ICLR 2025 Hallo3: Highly Dynamic and Realistic Portrait Image Animation with Video Diffusion Transformer CVPR 2025 OpenHumanVid: A Large-Scale High-Quality Dataset for Enhancing Human-Centric Video Generation CVPR 2025 Retaining Knowledge and Enhancing Long-Text Representations in CLIP through Dual-Teacher Distillation CVPR 2025 Scaling Down, Serving Fast: Compressing and Deploying Efficient LLMs for Recommendation Systems EMNLP 2025 Tora: Trajectory-oriented Diffusion Transformer for Video Generation CVPR 2025 Champ: Controllable and Consistent Human Image Animation with 3D Parametric Guidance ECCV 2024 EmoTalk3D: High-Fidelity Free-View Synthesis of Emotional 3D Talking Head ECCV 2024 Gaussian-Flow: 4D Reconstruction with Dynamic 3D Gaussian Particle CVPR 2024 Head360: Learning a Parametric 3D Full-Head for Free-View Synthesis in 360° ECCV 2024 High-Fidelity and Transferable NeRF Editing by Frequency Decomposition ECCV 2024 STAG4D: Spatial-Temporal Anchored Generative 4D Gaussians ECCV 2024 Monocular Scene Reconstruction with 3D SDF Transformers ICLR 2023 Neural Window Fully-Connected CRFs for Monocular Depth Estimation CVPR 2022 Quadtree Attention for Vision Transformers ICLR 2022 RCP: Recurrent Closest Point for Point Cloud CVPR 2022 CondLaneNet: A Top-To-Down Lane Detection Framework Based on Conditional Convolution ICCV 2021 FloorPlanCAD: A Large-Scale CAD Drawing Dataset for Panoptic Symbol Spotting ICCV 2021 Learning Camera Localization via Dense Scene Matching CVPR 2021 Cascade Cost Volume for High-Resolution Multi-View Stereo and Stereo Matching CVPR 2020 End-to-End Learning Local Multi-View Descriptors for 3D Point Clouds CVPR 2020 Self-Supervised Human Depth Estimation From Monocular Videos CVPR 2020 A Neural Network for Detailed Human Depth Estimation From a Single Image ICCV 2019 Batch DropBlock Network for Person Re-Identification and Beyond ICCV 2019 GeoDesc: Learning Local Descriptors by Integrating Geometry Constraints ECCV 2018 Learning and Matching Multi-View Descriptors for Registration of Point Clouds ECCV 2018 Very Large-Scale Global SfM by Distributed Motion Averaging CVPR 2018 Distributed Very Large Scale Bundle Adjustment by Global Camera Consensus ICCV 2017 Progressive Large Scale-Invariant Image Matching in Scale Space ICCV 2017 A Text Detection System for Natural Scenes With Convolutional Feature Learning and Cascaded Classification CVPR 2016 Joint Camera Clustering and Surface Segmentation for Large-Scale Multi-View Stereo ICCV 2015 Local Readjustment for High-Resolution 3D Reconstruction CVPR 2014