4 papers
GeoMix: Descriptor-Free Visual Localization via Global Context and Multi-Detector Training
Yejun Zhang, Xinjue Wang, Zihan Wang +2
Descriptor-free visual localization eliminates high-dimensional descriptor storage, preserves scene privacy, and simplifies map maintenance, yet its accuracy still lags far behind…
Finer Parameter Steps for Low-Rank PEFT: A Controlled Study with CP Tensor Adapters
Xinjue Wang, Xiuheng Wang, Yejun Zhang +3
Low-rank adapters are usually compared by sweeping a small set of ranks, but the rank also fixes the resolution of the parameter budget. For a OPT attention proj…
NVSMask3D: Hard Visual Prompting with Camera Pose Interpolation for 3D Open Vocabulary Instance Segmentation
Junyuan Fang, Zihan Wang, Yejun Zhang +3
Vision-language models (VLMs) have demonstrated impressive zero-shot transfer capabilities in image-level visual perception tasks. However, they fall short in 3D instance-level seg…
A2-GNN: Angle-Annular GNN for Visual Descriptor-free Camera Relocalization
Yejun Zhang, Shuzhe Wang, Juho Kannala
Visual localization involves estimating the 6-degree-of-freedom (6-DoF) camera pose within a known scene. A critical step in this process is identifying pixel-to-point corresponden…