D
Danfei Xu
Researcher at Stanford University
Publications - 55
Citations - 5766
Danfei Xu is an academic researcher from Stanford University. The author has contributed to research in topics: Computer science & Object (computer science). The author has an hindex of 19, co-authored 43 publications receiving 3612 citations. Previous affiliations of Danfei Xu include Columbia University & Carnegie Mellon University.
Papers
More filters
Book ChapterDOI
3D-R2N2: A Unified Approach for Single and Multi-view 3D Object Reconstruction
TL;DR: 3D-R2N2 as discussed by the authors proposes a 3D Recurrent Reconstruction Neural Network that learns a mapping from images of objects to their underlying 3D shapes from a large collection of synthetic data.
Proceedings ArticleDOI
Scene Graph Generation by Iterative Message Passing
TL;DR: In this article, the problem of graph generation is formulated as message passing between the primal node graph and its dual edge graph, which can take advantage of contextual cues to make better predictions on objects and their relationships.
Proceedings ArticleDOI
DenseFusion: 6D Object Pose Estimation by Iterative Dense Fusion
TL;DR: DenseFusion as mentioned in this paper proposes a heterogeneous architecture that processes the two complementary data sources individually and uses a novel dense fusion network to extract pixel-wise dense feature embedding, from which the pose is estimated.
Proceedings ArticleDOI
PointFusion: Deep Sensor Fusion for 3D Bounding Box Estimation
TL;DR: PointFusion as mentioned in this paper is a generic 3D object detection method that leverages both image and 3D point cloud information, which predicts multiple 3D box hypotheses and their confidences using the input 3D points as spatial anchors.
Posted Content
3D-R2N2: A Unified Approach for Single and Multi-view 3D Object Reconstruction
TL;DR: The 3D-R2N2 reconstruction framework outperforms the state-of-the-art methods for single view reconstruction, and enables the 3D reconstruction of objects in situations when traditional SFM/SLAM methods fail (because of lack of texture and/or wide baseline).