I was born on Oct 10th, 2000 in Dengfeng, China, which is home to various religious institutions and famous temples and located at the foot of the Mount Song, one of the most sacred mountains in China.
I alse took many Biology & Chemistry courses during my initial 2 years in University.
Research interests
My research interests are computer vision, machine learning and multi modal, specifically, learning-based methods for 3D shape analysis, Geometry processing, Neural implicit representation, Generation, etc.
I am working at the intersection between Machine learning and Computer Vision,
developing new machine learning methods to resolve the challenging problems in 3D Vision,
especially focus on Reconstruction and Scene Understanding.
My long-term goal is to improve the application of 3D Vision,
benefiting society directly by improving people's living environment.
Much of my research is about inferring the physical world (shape, motion, color, light, etc) from images and 3D raw data.
Representative papers are highlighted.
We leverage the 3D geometry information in 3D point cloud, the
projection relationship between 3D point cloud and multi-view 2D posed RGB-D
frames and the semantic features extracted by CLIP from multi-view 2D posed
RGB-D frames to address the challenge of 3D instance segmentation.
Similar to how humans perceive 3D objects, neural networks discern the class labels of point clouds by combining local and global features of the structures and performance.
Based on this, we reviewed the pipeline of few-shot point cloud semantic segmentation and identified three issues.
Meta-learning plays an increasingly importantt role in AutoML.
A key sub-problemāmeta-learning from learning curves is an mmature but gradually attention area within the field of meta-learning.
I use 3D Gaussain Splating to build a novel robotics simulator,
the physical simulation is implemented by ISSAC SIM while the photorealistic render is implemented ny 3DGS.
I use 3D Gaussian Splatting to reconstruct some scene of Guangfulin taken by myself. Guangfulin is a beautiful park in Songjiang District, Shanghai, China.
We gather the wiki pedia knowledge about science questions to make it into a RAG(Retrieval Augmented Generation) task,
then we make three Deberta models with different finetuning and combine their output features to infer the right answer.
The implementation of RandLA-Net(CVPR2020) is in code0 (for large-scale semantic segmentation).
and SQN(ECCV2022) is in code1 (for weak supervision schemes).
We use a integration of ViT OFA and BLIP to make predictions on a dataset containing a wide variety of (prompt, image) pairs generated by Stable Diffusion 2.0.
Misc
Musicš¶:
       
I like playing the pianoš¹ and have obtained certification in piano grade 10 from Shanghai Conservatory of Music.
Sportsšāāļø:
       
I like playing basketballš and I am a fun of NBA star Paul George.
       
badmintonšø, swimšāāļø and etc.