Pinned Repositories
habitat-lab
A modular high-level library to train embodied AI agents across a variety of tasks and environments.
IntrotoCV
RVAL
3DAwareNav
[CVPR 2023] We propose a framework for the challenging 3D-aware ObjectNav based on two straightforward sub-policies. The two sub-polices, namely corner-guided exploration policy and category-aware identification policy, simultaneously perform by utilizing online fused 3D points as observation.
FusionAwareConv
[CVPR 2020] We propose a novel fusionaware 3D point convolution which operates directly on the geometric surface being reconstructed and exploits effectively the inter-frame correlation for high quality 3D feature learning.
jzhzhang.github.io
ROSEFusion
[SIGGRAPH 2021] ROSEFusion is proposed to tackle the difficulties in fast-motion camera tracking using random optimization with depth information only.
NaVid
DriveVLM
gamma
jzhzhang's Repositories
jzhzhang/ROSEFusion
[SIGGRAPH 2021] ROSEFusion is proposed to tackle the difficulties in fast-motion camera tracking using random optimization with depth information only.
jzhzhang/FusionAwareConv
[CVPR 2020] We propose a novel fusionaware 3D point convolution which operates directly on the geometric surface being reconstructed and exploits effectively the inter-frame correlation for high quality 3D feature learning.
jzhzhang/3DAwareNav
[CVPR 2023] We propose a framework for the challenging 3D-aware ObjectNav based on two straightforward sub-policies. The two sub-polices, namely corner-guided exploration policy and category-aware identification policy, simultaneously perform by utilizing online fused 3D points as observation.
jzhzhang/jzhzhang.github.io