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

Constructing a 3D scene capable of accommodating open-ended language queries, is a
pivotal pursuit in the domain of robotics, which facilitates robots in executing object …

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 …

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

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 …

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 …

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 …

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 …

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 …

Learning-based methods to solve dense 3D vision problems typically train on 3D sensor
data. The respectively used principle of measuring distances provides advantages and …