Related papers: Adapt3R: Adaptive 3D Scene Representation for Doma…
Robotic systems often require precise scene analysis capabilities, especially in unstructured, cluttered situations, as occurring in human-made environments. While current deep-learning based methods yield good estimates of object poses,…
Streaming 3D perception is well suited to robotics and augmented reality, where long visual streams must be processed efficiently and consistently. Recent recurrent models offer a promising solution by maintaining fixed-size states and…
In this paper, we target the adaptive source driven 3D scene editing task by proposing a CustomNeRF model that unifies a text description or a reference image as the editing prompt. However, obtaining desired editing results conformed with…
Realizing active visual tracking with a single unified model across diverse robots is challenging, as the physical constraints and motion dynamics vary drastically from one platform to another. Existing approaches typically train separate…
The transformation towards intelligence in various industries is creating more demand for intelligent and flexible products. In the field of robotics, learning-based methods are increasingly being applied, with the purpose of training…
Humans can perceive scenes in 3D from a handful of 2D views. For AI agents, the ability to recognize a scene from any viewpoint given only a few images enables them to efficiently interact with the scene and its objects. In this work, we…
In agricultural automation, inherent occlusion presents a major challenge for robotic harvesting. We propose a novel imitation learning-based viewpoint planning approach to actively adjust camera viewpoint and capture unobstructed images of…
Careful robot manipulation in every-day cluttered environments requires an accurate understanding of the 3D scene, in order to grasp and place objects stably and reliably and to avoid colliding with other objects. In general, we must…
Existing approaches to Implicit Neural Representation (INR) can be interpreted as a global scene representation via a linear combination of Fourier bases of different frequencies. However, such universal basis functions can limit the…
Recent advancements in 3D robotic manipulation have improved grasping of everyday objects, but transparent and specular materials remain challenging due to depth sensing limitations. While several 3D reconstruction and depth completion…
We consider the problem of adapting a network trained on three-channel color images to a hyperspectral domain with a large number of channels. To this end, we propose domain adaptor networks that map the input to be compatible with a…
While Reinforcement Learning (RL) agents can successfully learn to handle complex tasks, effectively generalizing acquired skills to unfamiliar settings remains a challenge. One of the reasons behind this is the visual encoders used are…
Existing methods for arbitrary-shaped text detection in natural scenes face two critical issues, i.e., 1) fracture detections at the gaps in a text instance; and 2) inaccurate detections of arbitrary-shaped text instances with diverse…
Embodied scene understanding requires not only comprehending visual-spatial information that has been observed but also determining where to explore next in the 3D physical world. Existing 3D Vision-Language (3D-VL) models primarily focus…
Visual imitation learning provides a framework for learning complex manipulation behaviors by leveraging human demonstrations. However, current interfaces for imitation such as kinesthetic teaching or teleoperation prohibitively restrict…
Dynamic quadruped locomotion over challenging terrains with precise foot placements is a hard problem for both optimal control methods and Reinforcement Learning (RL). Non-linear solvers can produce coordinated constraint satisfying…
For humans, visual understanding is inherently generative: given a 3D shape, we can postulate how it would look in the world; given a 2D image, we can infer the 3D structure that likely gave rise to it. We can thus translate between the 2D…
Absolute camera pose regressors estimate the position and orientation of a camera from the captured image alone. Typically, a convolutional backbone with a multi-layer perceptron head is trained with images and pose labels to embed a single…
Learning generalizable robotic manipulation policies remains a key challenge due to the scarcity of diverse real-world training data. While recent approaches have attempted to mitigate this through self-supervised representation learning,…
3D scene understanding has gained significant attention due to its wide range of applications. However, existing methods for 3D scene understanding are limited to specific downstream tasks, which hinders their practicality in real-world…