Jiazhao Zhang | 张嘉曌

I am a Ph.D. student at the Center on Frontiers of Computing Studies , Peking University, advised by Prof. He Wang since 2022. Before this, I obtained my M.S. degree and B.Eng. degree from NUDT and Shandong University, respectively. During my master's studies, I was fortunate to be supervised by Prof. Kai Xu and had the opportunity to work closely with Prof. Chenyang Zhu.

I'm interested in indoor scene reconstruction, understanding and interaction. More specifically, I work on building robust and practical systems for home robots.

Email  /  Google Scholar  /  Github

*: equal contribution; ^†: corresponding author(s)

NaVid makes the first endeavour to showcase the capability of VLMs to achieve state-of-the-art level navigation performance without any maps, odometer and depth inputs. Following human instruction, NaVid only requires an on-the-fly video stream from a monocular RGB camera equipped on the robot to output the next-step action.

We propose a robust zero-shot 3D instance segmentation method that leverages the 3D view consensus of 2D candidate masks. Our method can integrate with a 2D visual foundation model (e.g., CLIP) to achieve open-vocabulary 3D instance segmentation.

We propose a graspability-aware mobile manipulation approach powered by an online grasping pose fusion framework that enables a temporally consistent grasping observation.

We introduce MIPS-Fusion, a robust and scalable online RGB-D reconstruction method based on a novel neural implicit representation – multi-implicit-submap.

We propose a framework for the challenging 3D-aware ObjectNav based on two straightforward sub-policies, namely corner-guided exploration policy and category-aware identification policy.

To realize efficient random optimization in the 18D state space of IMU tracking, we propose to identify and sample particles from active subspace.

We propose to tackle the difficulties of fast-motion camera tracking in the absence of inertial measurements using random optimization.

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.

We propose a novel approach to robot-operated active understanding of unknown indoor scenes, based on online RGBD reconstruction with semantic segmentation.