Related papers: 3D Equivariant Visuomotor Policy Learning via Sphe…

This paper proposes Instruct 4D-to-4D that achieves 4D awareness and spatial-temporal consistency for 2D diffusion models to generate high-quality instruction-guided dynamic scene editing results. Traditional applications of 2D diffusion…

Monocular depth estimation is a crucial task in computer vision. While existing methods have shown impressive results under standard conditions, they often face challenges in reliably performing in scenarios such as low-light or rainy…

In the field of Robot Learning, the complex mapping between high-dimensional observations such as RGB images and low-level robotic actions, two inherently very different spaces, constitutes a complex learning problem, especially with…

Data augmentation in feature space is effective to increase data diversity. Previous methods assume that different classes have the same covariance in their feature distributions. Thus, feature transform between different classes is…

Diffusion policies generate robot motions by learning to denoise action-space trajectories conditioned on observations. These observations are commonly streams of RGB images, whose high dimensionality includes substantial task-irrelevant…

Precise robot manipulations require rich spatial information in imitation learning. Image-based policies model object positions from fixed cameras, which are sensitive to camera view changes. Policies utilizing 3D point clouds usually…

We propose a novel 3d colored shape reconstruction method from a single RGB image through diffusion model. Diffusion models have shown great development potentials for high-quality 3D shape generation. However, most existing work based on…

This paper focuses on enhancing the grasping precision and generalization of manipulation policies learned via imitation learning. Diffusion-based policy learning methods have recently become the mainstream approach for robotic manipulation…

Recently, equivariant neural network models have been shown to improve sample efficiency for tasks in computer vision and reinforcement learning. This paper explores this idea in the context of on-robot policy learning in which a policy…

Generalizable 3D object reconstruction from single-view RGB-D images remains a challenging task, particularly with real-world data. Current state-of-the-art methods develop Transformer-based implicit field learning, necessitating an…

Diffusion models have seen rapid adoption in robotic imitation learning, enabling autonomous execution of complex dexterous tasks. However, action synthesis is often slow, requiring many steps of iterative denoising, limiting the extent to…

Recent advances in diffusion$/$flow-matching policies have enabled imitation learning of complex, multi-modal action trajectories. However, they are computationally expensive because they sample a trajectory of trajectories: a…

Spherical data is found in many applications. By modeling the discretized sphere as a graph, we can accommodate non-uniformly distributed, partial, and changing samplings. Moreover, graph convolutions are computationally more efficient than…

3D policy learning promises superior generalization and cross-embodiment transfer, but progress has been hindered by training instabilities and severe overfitting, precluding the adoption of powerful 3D perception models. In this work, we…

Equivariant diffusion policies (EDPs) combine the generative expressivity of diffusion models with the strong generalization and sample efficiency afforded by geometric symmetries. While steering these policies with reinforcement learning…

We present a novel approach for single-image mesh texturing, which employs a diffusion model with judicious conditioning to seamlessly transfer an object's texture from a single RGB image to a given 3D mesh object. We do not assume that the…

Omnidirectional vision is becoming increasingly relevant as more efficient $360^o$ image acquisition is now possible. However, the lack of annotated $360^o$ datasets has hindered the application of deep learning techniques on spherical…

Depth sensing is an important problem for 3D vision-based robotics. Yet, a real-world active stereo or ToF depth camera often produces noisy and incomplete depth which bottlenecks robot performances. In this work, we propose D3RoMa, a…

End-to-end learning for visual robotic manipulation is known to suffer from sample inefficiency, requiring large numbers of demonstrations. The spatial roto-translation equivariance, or the SE(3)-equivariance can be exploited to improve the…

This work seeks to improve the generalization and robustness of existing neural networks for 3D point clouds by inducing group equivariance under general group transformations. The main challenge when designing equivariant models for point…