Learning powerful representations in bird's-eye-view (BEV) for perception tasks is trending
and drawing extensive attention both from industry and academia. Conventional …

Multi-sensor fusion is essential for an accurate and reliable autonomous driving system.
Recent approaches are based on point-level fusion: augmenting the LiDAR point cloud with …

We present Theseus, an efficient application-agnostic open source library for differentiable
nonlinear least squares (DNLS) optimization built on PyTorch, providing a common …

Object pose estimation is a core perception task that enables, for example, object
manipulation and scene understanding. The widely available, inexpensive, and high …

We propose a Pose-Free Large Reconstruction Model (PF-LRM) for reconstructing a 3D
object from a few unposed images even with little visual overlap, while simultaneously …

In this paper, we address the problem of detecting 3D objects from multi-view images.
Current query-based methods rely on global 3D position embeddings (PE) to learn the …

The two-stage object pose estimation paradigm first detects semantic keypoints on the
image and then estimates the 6D pose by minimizing reprojection errors. Despite performing …

Despite various probabilistic methods for modeling the uncertainty and ambiguity in human
mesh recovery, their overall precision is limited because existing formulations for joint …

Cross-modality registration between 2D images captured by cameras and 3D point clouds
from LiDARs is a crucial task in computer vision and robotic. Previous methods estimate 2D …

Most recent 6D object pose estimation methods rely on 2D optical flow networks to refine
their results. However, these optical flow methods typically do not consider any 3D shape …