Nan Wang   王楠

I am a final-year Computer Science Master's student at CAD Research Center, Tongji University, and currently an Algorithm Researcher Intern at BAAI. My research focuses on neural rendering and world models, exploring their potential applications in robotics, VR, and autonomous driving.

Email  /  Google Scholar  /  Github /  Linkedin

News

Research

Representative papers are highlighted.

We use Multi-Scale Bilateral Grids that improves geometric accuracy in driving scene reconstruction through enhancing photometric consistency.

We reconstruct 3D objects using the Gaussian splatting representation and predicts various physical properties in a zero-shot manner.

We leverage the 3D geometry information and the semantic features to address the challenge of 3D instance segmentation.

We use semantic features derived from 2D foundation model to revolutionize the material property optimization for 3DGS.

A key sub-problem: meta-learning from learning curves is an mature but gradually attention area within the field of meta-learning.

We combine local and global features of the structures and performance to perform few-shot point cloud semantic segmentation.

Projects

We use 3D Gaussain Splating to build a novel robotics simulator, the physical simulation is implemented by ISAAC SIM while the photorealistic render is implemented by 3DGS.

I use 3D Gaussian Splatting and nerfstudio to build an implementation, which can accomplish the 3D scene decomposition and Reconstruction.

RandLA-Net (CVPR2020) is a light net which can process efficient semantic segmentation for 3D point clouds, and SQN (ECCV2022) achieves promising performance on seven large-scale open datasets under weak supervision schemes.

LLM4Science 🥈 silver medal solution. We make it into a RAG (Retrieval Augmented Generation) task and finetune three Deberta models with different finetuning and combine their output features to infer the right answer.

Short Bio

Misc

Feel free to steal this website's source code. Do not scrape the HTML from this page itself, as it includes analytics tags that you do not want on your own website — use the github code instead. Also, consider using Leonid Keselman's Jekyll fork of this page.