Qihao Liu

CrossFlow. [CVPR2025] PyTorch-based reimplementation of CrossFlow, as proposed in 'Flowing from Words to Pixels: A Noise-Free Framework for Cross-Modality Evolution'

direct3d. [CVPR24] DIRECT-3D: Learning Direct Text-to-3D Generation on Massive Noisy 3D Data

DiMR. [NeurIPS 24] Alleviating Distortion in Image Generation via Multi-Resolution Diffusion Models

PoseExaminer. [CVPR23] PoseExaminer: Automated Testing of Out-of-Distribution Robustness in Human Pose and Shape Estimation

HUPOR. Explicit Occlusion Reasoning for Multi-person 3D Human Pose Estimation