Nana Wang   王楠

I am a Second-year Computer Science Master's student at CAD Research Center, Tongji University.

My research interests focus on 3D Vision(Neural rendering, 3dgs, Multi View Stereo, etc).

If you find any research interests that we might share, feel free to drop me an email. I am always open to potential collaborations.

Email  /  CV  /  Google Scholar  /  Github /  Linkedin

中文 / English
 日本語(learning)/ français(learning)

• [10/2024] I have been on an internship at Shanghai Noematrix Intelligence Technology Ltd.
• [05/2024] I have been on an internship at Xiaomi Robot Technology.
• [12/2023] I have been on a research internship at Institute for Al Industry Research (AIR), Tsinghua University.

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-problem—meta-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 and nerfstudio to build a implementation, which can accomplish the 3D scene decomposition and Reconstruction.

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.