Search Results for author:
Found 8 papers, 6 papers with code
Neural Point Light Fields
We introduce Neural Point Light Fields that represent scenes implicitly with a light field living on a sparse point cloud.
Revisiting Point Cloud Shape Classification with a Simple and Effective Baseline
It also outperforms state-of-the-art methods on ScanObjectNN, a real-world point cloud benchmark, and demonstrates better cross-dataset generalization.
Ranked #13 on
Point Cloud Classification
on PointCloud-C
Revisiting Point Cloud Classification with a Simple and Effective Baseline
It also outperforms state-of-the-art methods on ScanObjectNN, a real-world point cloud benchmark, and demonstrates better cross-dataset generalization.
Ranked #10 on
3D Point Cloud Classification
on ModelNet40-C
How Useful is Self-Supervised Pretraining for Visual Tasks?
We investigate what factors may play a role in the utility of these pretraining methods for practitioners.
Feature Partitioning for Efficient Multi-Task Architectures
Multi-task learning holds the promise of less data, parameters, and time than training of separate models.
Associative Embedding: End-to-End Learning for Joint Detection and Grouping
We introduce associative embedding, a novel method for supervising convolutional neural networks for the task of detection and grouping.
Ranked #5 on
Keypoint Detection
on OCHuman
Stacked Hourglass Networks for Human Pose Estimation
This work introduces a novel convolutional network architecture for the task of human pose estimation.
Ranked #1 on
Pose Estimation
on FLIC Wrists
