Reconstructing hand-held objects from a single RGB image is an important and challenging
problem. Existing works utilizing Signed Distance Fields (SDF) reveal limitations in …

Despite the growing demand for accurate surface normal estimation models existing
methods use general-purpose dense prediction models adopting the same inductive biases …

Object rearrangement is pivotal in robotic-environment interactions, representing a
significant capability in embodied AI. In this paper, we present SG-Bot, a novel …

Estimating 6D object poses is a major challenge in 3D computer vision. Building on
successful instance-level approaches research is shifting towards category-level pose …

Reliable multi-agent trajectory prediction is crucial for the safe planning and control of
autonomous systems. Compared with single-agent cases, the major challenge in …

Category-level object pose estimation aiming to predict the 6D pose and 3D size of objects
from known categories typically struggles with large intra-class shape variation. Existing …

Monocular 3D object detection has recently made a significant leap forward thanks to the
use of pre-trained depth estimators for pseudo-LiDAR recovery. Yet, such two-stage …

Robotic gras** in clutters is a fundamental task in robotic manipulation. In this work, we
propose an economic framework for 6-DoF grasp detection, aiming to economize the …

Previous works concerning single-view hand-held object reconstruction typically rely on
supervision from 3D ground-truth models which are hard to collect in real world. In contrast …

In this work we present a novel dense-correspondence method for 6DoF object pose
estimation from a single RGB-D image. While many existing data-driven methods achieve …