1 citations · 1 across the 9 of their papers we have counts for
7 papers · 1 filter
RoofGS: Roofline-Guided End-to-End Acceleration of 3D Gaussian Splatting
Yang Luo, Yan Gong, Yongsheng Gao +1
3D Gaussian Splatting (3DGS) enables real-time novel-view synthesis but remains limited on GPUs at high resolutions. Through a stage-wise Roofline characterization, we identify two…
Local-GS: Accelerating 3D Gaussian Splatting via Tile-Local Warp Coherence
Yang Luo, Yan Gong, Yongsheng Gao +3
3D Gaussian Splatting (3DGS) has significantly advanced real-time novel view synthesis by representing scenes as dense collections of anisotropic 3D Gaussian primitives. However, t…
Semantic Prior Guided One-View 6D Pose Estimation for Novel Objects
Yang Luo, Yan Gong, Yongsheng Gao
In many practical 6D object pose estimation scenarios, we often have access to only a single real-world RGB-D reference view per object, typically without CAD models. Existing meth…
MAPRPose: Mask-Aware Proposal and Amodal Refinement for Multi-Object 6D Pose Estimation
Yang Luo, Yan Gong, Yongsheng Gao +2
6D object pose estimation in cluttered scenes remains challenging due to severe occlusion and sensor noise. We propose MAPRPose, a two-stage framework that leverages mask-aware cor…
DiffPixelFormer: Differential Pixel-Aware Transformer for RGB-D Indoor Scene Segmentation
Yan Gong, Jianli Lu, Yongsheng Gao +3
Indoor semantic segmentation is fundamental to computer vision and robotics, supporting applications such as autonomous navigation, augmented reality, and smart environments. Altho…
Stable at Any Speed: Speed-Driven Multi-Object Tracking with Learnable Kalman Filtering
Yan Gong, Mengjun Chen, Hao Liu +5
Multi-object tracking (MOT) enables autonomous vehicles to continuously perceive dynamic objects, supplying essential temporal cues for prediction, behavior understanding, and safe…