5 papers
Noise-Robust Tiny Object Localization with Flows
Huixin Sun, Linlin Yang, Ronyu Chen +4
Despite significant advances in generic object detection, a persistent performance gap remains for tiny objects compared to normal-scale objects. We demonstrate that tiny objects a…
AnchorDS: Anchoring Dynamic Sources for Semantically Consistent Text-to-3D Generation
Jiayin Zhu, Linlin Yang, Yicong Li +1
Optimization-based text-to-3D methods distill guidance from 2D generative models via Score Distillation Sampling (SDS), but implicitly treat this guidance as static. This work show…
InstructHumans: Editing Animated 3D Human Textures with Instructions
Jiayin Zhu, Linlin Yang, Angela Yao
We present InstructHumans, a novel framework for instruction-driven {animatable} 3D human texture editing. Existing text-based 3D editing methods often directly apply Score Distill…
Analyzing the Synthetic-to-Real Domain Gap in 3D Hand Pose Estimation
Zhuoran Zhao, Linlin Yang, Pengzhan Sun +2
Recent synthetic 3D human datasets for the face, body, and hands have pushed the limits on photorealism. Face recognition and body pose estimation have achieved state-of-the-art pe…
Online Test-time Adaptation for 3D Human Pose Estimation: A Practical Perspective with Estimated 2D Poses
Qiuxia Lin, Kerui Gu, Linlin Yang +1
Online test-time adaptation for 3D human pose estimation is used for video streams that differ from training data. Ground truth 2D poses are used for adaptation, but only estimated…