activity
20202022
most citedPolyLoss: A Polynomial Expansion Perspective of Classification Loss Functions

85 citations · 211 across the 20 of their papers we have counts for

collaborators

21 papers

cs.CV20223 cited

NeRDi: Single-View NeRF Synthesis with Language-Guided Diffusion as General Image Priors

Congyue Deng, Chiyu "Max'' Jiang, Charles R. Qi +4

2D-to-3D reconstruction is an ill-posed problem, yet humans are good at solving this problem due to their prior knowledge of the 3D world developed over years. Driven by this obser…

cs.CV2022

LidarAugment: Searching for Scalable 3D LiDAR Data Augmentations

Zhaoqi Leng, Guowang Li, Chenxi Liu +5

Data augmentations are important in training high-performance 3D object detectors for point clouds. Despite recent efforts on designing new data augmentations, perhaps surprisingly…

cs.CV202217 cited

PseudoAugment: Learning to Use Unlabeled Data for Data Augmentation in Point Clouds

Zhaoqi Leng, Shuyang Cheng, Benjamin Caine +5

Data augmentation is an important technique to improve data efficiency and save labeling cost for 3D detection in point clouds. Yet, existing augmentation policies have so far been…

cs.RO20221 cited

Hierarchical Model-Based Imitation Learning for Planning in Autonomous Driving

Eli Bronstein, Mark Palatucci, Dominik Notz +14

We demonstrate the first large-scale application of model-based generative adversarial imitation learning (MGAIL) to the task of dense urban self-driving. We augment standard MGAIL…

cs.CV20223 cited

CramNet: Camera-Radar Fusion with Ray-Constrained Cross-Attention for Robust 3D Object Detection

Jyh-Jing Hwang, Henrik Kretzschmar, Joshua Manela +4

Robust 3D object detection is critical for safe autonomous driving. Camera and radar sensors are synergistic as they capture complementary information and work well under different…

cs.CV2022

Improving the Intra-class Long-tail in 3D Detection via Rare Example Mining

Chiyu Max Jiang, Mahyar Najibi, Charles R. Qi +2

Continued improvements in deep learning architectures have steadily advanced the overall performance of 3D object detectors to levels on par with humans for certain tasks and datas…