CoGeo-GS: Concept-Driven and Geometry-Aware Multi-Object Removal in 3D Scenes
针对3D场景中多物体移除难题，提出CoGeo-GS框架，通过概念驱动和几何感知方法优化物体选择与几何恢复，提升视觉质量和重建保真度。
0 citationsRead paper
Selected work
Representative Papers
Egocentric Visibility-Aware Human Pose Estimation
This study addresses the performance degradation in egocentric human pose estimation caused by occluded or invisible keypoints, a challenge commonly overlooked by existing methods that neglect visibility disparities. To tackle this issue, the authors introduce keypoint visibility annotations for the first time, construct a large-scale dataset named Eva-3M, and augment the existing EMHI dataset with visibility labels. They further propose EvaPose, the first pose estimation method that explicitly models keypoint visibility. Extensive experiments demonstrate that EvaPose achieves state-of-the-art performance on both Eva-3M and EMHI, confirming that incorporating visibility information significantly enhances the accuracy of visible keypoint prediction.
0 citationsRead paper
Recent publications
Latest Papers
CoGeo-GS: Concept-Driven and Geometry-Aware Multi-Object Removal in 3D Scenes
针对3D场景中多物体移除难题，提出CoGeo-GS框架，通过概念驱动和几何感知方法优化物体选择与几何恢复，提升视觉质量和重建保真度。
0 citationsRead paper
Egocentric Visibility-Aware Human Pose Estimation
This study addresses the performance degradation in egocentric human pose estimation caused by occluded or invisible keypoints, a challenge commonly overlooked by existing methods that neglect visibility disparities. To tackle this issue, the authors introduce keypoint visibility annotations for the first time, construct a large-scale dataset named Eva-3M, and augment the existing EMHI dataset with visibility labels. They further propose EvaPose, the first pose estimation method that explicitly models keypoint visibility. Extensive experiments demonstrate that EvaPose achieves state-of-the-art performance on both Eva-3M and EMHI, confirming that incorporating visibility information significantly enhances the accuracy of visible keypoint prediction.
0 citationsRead paper