Songlin Wei 魏松林

I'm a PhD student at school of computer science of Peking University advised by Prof. He Wang.

I earned my Bachelor of Software Engineering degree from Xiamen University. Over the years, my career has undergone various transformations. I developed large social media websites, built robots, and started companies.

I finally found my passion in doing research and went to Soochow University and had worked closely with Prof. Guodong Chen and Prof. WenZheng Chi.

Email  /  GitHub  /  Google Scholar  /  Wechat

profile photo

Publications

My research interests include 3D computer vision, robotic learning and Embodied AI. I'm currently working on Vision-Language-Action models for robotics.

project image

D3RoMa: Disparity Diffusion-based Depth Sensing for Material-Agnostic Robotic Manipulation


Songlin Wei, Haoran Geng, Jiayi Chen, Congyue Deng, Wenbo Cui, Chengyang Zhao, Xiaomeng Fang, Leonidas Guibas, He Wang†
Under Review, 2024

We propose D3RoMa, a diffusion model-based depth estimation framework on stereo image pairs for robotic manipulation.

project image

Make a Donut🍩: Hierarchical EMD-Space Planning for Zero-Shot Deformable Manipulation with Tools


Yang You, Bokui Shen, Congyue Deng, Haoran Geng, He Wang, Songlin Wei, Leonidas Guibas†
Under Review, 2024

In this work, we introduce a demonstration-free hierarchical planning approach capable of tackling intricate long-horizon tasks without necessitating any training

project image

Open6DOR: Benchmarking Open-instruction 6-DoF Object Rearrangement and A VLM-based Approach


Yufei Ding*, Haoran Geng*, Chaoyi Xu, Xiaomeng Fang, Jiazhao Zhang, Songlin Wei, Qiyu Dai, Zhizheng Zhang, He Wang†
CVPR 2024 @ VLADA, 2024
website /

We present Open6DOR, a challenging and comprehensive benchmark for open-instruction 6-DoF object rearrangement tasks. Following this, we propose a zero-shot and robust method, Open6DORGPT, which proves effective in demanding simulation environments and real-world scenarios.

project image

SAGE🌿: Bridging Semantic and Actionable Parts for Generalizable Manipulation of Articulated Objects


Haoran Geng*, Songlin Wei*, Congyue Deng, Bokui Shen, He Wang†, Leonidas Guibas†
RSS, 2024
arxiv / website /

We present SAGE🌿, a framework bridging the understanding of semantic and actionable parts for generalizable manipulation of articulated objects.

project image

FG-NeRF: Flow-GAN based Probabilistic Neural Radiance Field for Independence-Assumption-Free Uncertainty Estimation


Songlin Wei*, Jiazhao Zhang*, Yang Wang, Fanbo Xiang, Hao Su, He Wang
Arxiv, 2023
arxiv /

We propose an independence-assumption-free probabilistic neural radiance field based on Flow-GAN. By combining the generative capability of adversarial learning and the powerful expressivity of normalizing flow, our method explicitly models the density-radiance distribution of the whole scene.

project image

3D Object Aided Self-Supervised Monocular Depth Estimation


Songlin Wei, Guodong Chen, Wenzheng Chi, Zhenhua Wang and Lining Sun
IROS, 2022
arxiv / video /

Self-supervised depth estimation methods rely on static world assumption, which produce inaccurate depths of dynamic objects. In this work, we propose to address dynamic object movements through monocular 3D object detection.

project image

Object Clustering with Dirichlet Process Mixture Model for Data Association in Monocular SLAM


Songlin Wei, Guodong Chen, Wenzheng Chi, Zhenhua Wang and Lining Sun
IEEE Transactions on Industrial Electronics, 2022
arxiv / video /

We propose a novel data association method for cuboid landmarks based on Dirichlet Process Mixture Model. By jointly considering object class, position, and size, our method can perform data association robustly.






Forked from Leonid Keselman's website