1

Transfer Your Perspective: Controllable 3D Generation from Any Viewpoint in a Driving Scene
Self-driving cars relying solely on ego-centric perception face limitations in sensing, often failing to detect occluded, faraway …
PDF Cite arXiv
Transfer Your Perspective: Controllable 3D Generation from Any Viewpoint in a Driving Scene
Learning 3D Perception from Others' Predictions
Accurate 3D object detection in real-world environments requires a huge amount of annotated data with high quality. Acquiring such data …
PDF Cite Project arXiv
Learning 3D Perception from Others' Predictions
Pre-Training LiDAR-Based 3D Object Detectors Through Colorization
Accurate 3D object detection and understanding for self-driving cars heavily relies on LiDAR point clouds, necessitating large amounts …
PDF Cite arXiv
Pre-Training LiDAR-Based 3D Object Detectors Through Colorization
Towards Open-World Segmentation of Parts
Segmenting object parts such as cup handles and animal bodies is important in many real-world applications but requires more annotation …
PDF Cite Code arXiv
Towards Open-World Segmentation of Parts
One Step at a Time: Long-Horizon Vision-and-Language Navigation with Milestones
We study the problem of developing autonomous agents that can follow human instructions to infer and perform a sequence of actions to …
PDF Cite arXiv
One Step at a Time: Long-Horizon Vision-and-Language Navigation with Milestones
Learning with Free Object Segments for Long-Tailed Instance Segmentation
One fundamental challenge in building an instance segmen- tation model for a large number of classes in complex scenes is the lack of …
PDF Cite arXiv
Learning with Free Object Segments for Long-Tailed Instance Segmentation
On Model Calibration for Long-Tailed Object Detection and Instance Segmentation
Vanilla models for object detection and instance segmentation suffer from the heavy bias toward detecting frequent objects in the …
PDF Cite Code arXiv
On Model Calibration for Long-Tailed Object Detection and Instance Segmentation
MosaicOS: A Simple and Effective Use of Object-Centric Images for Long-Tailed Object Detection
Many objects do not appear frequently enough in complex scenes (e.g., certain handbags in living rooms) for training an accurate object …
PDF Cite Code arXiv
MosaicOS: A Simple and Effective Use of Object-Centric Images for Long-Tailed Object Detection