- [2022/03] "Understanding 3D Object Articulation in Internet Videos" is accepted at CVPR 2022!
- [2021/07] "Planar Surface Reconstruction from Sparse Views" is accepted at ICCV 2021!
- [2021/04] I will have an internship at Facebook AI Research with Georgia Gkioxari this summer!
My research focuses on 3D vision and recognition, i.e. how do we recover the 3D world from one or few 2D images? The wall above demonstrates different 3D representations we extract from 2D images in my recent research projects.
We propose ViewSeg, which takes as input a few RGB images of a new scene and recognizes the scene from novel viewpoints by segmenting it into semantic categories.
We present Associative3D, which addresses 3D volumetric reconstruction from two views of a scene with an unknown camera, by simultaneously reconstructing objects and figuring out their relationship.
We present Open Annotations of Single Image Surfaces (OASIS), a dataset for single-image 3D in the wild consisting of dense annotations of detailed 3D geometry for Internet images.