Related papers: 3D-MVP: 3D Multiview Pretraining for Robotic Manip…
Visual robotic manipulation research and applications often use multiple cameras, or views, to better perceive the world. How else can we utilize the richness of multi-view data? In this paper, we investigate how to learn good…
In this work, we explore self-supervised visual pre-training on images from diverse, in-the-wild videos for real-world robotic tasks. Like prior work, our visual representations are pre-trained via a masked autoencoder (MAE), frozen, and…
Recent work on visual representation learning has shown to be efficient for robotic manipulation tasks. However, most existing works pretrained the visual backbone solely on 2D images or egocentric videos, ignoring the fact that robots…
General visual representations learned from web-scale datasets for robotics have achieved great success in recent years, enabling data-efficient robot learning on manipulation tasks; yet these pre-trained representations are mostly on 2D…
We present a new pre-training strategy called M$^{3}$3D ($\underline{M}$ulti-$\underline{M}$odal $\underline{M}$asked $\underline{3D}$) built based on Multi-modal masked autoencoders that can leverage 3D priors and learned cross-modal…
Current popular backbones in computer vision, such as Vision Transformers (ViT) and ResNets are trained to perceive the world from 2D images. However, to more effectively understand 3D structural priors in 2D backbones, we propose Mask3D to…
In this work, we focus on unsupervised vision-language-action mapping in the area of robotic manipulation. Recently, multiple approaches employing pre-trained large language and vision models have been proposed for this task. However, they…
The 3D visual grounding task aims to ground a natural language description to the targeted object in a 3D scene, which is usually represented in 3D point clouds. Previous works studied visual grounding under specific views. The…
The Vision Transformer (ViT) has demonstrated remarkable performance in Self-Supervised Learning (SSL) for 3D medical image analysis. Masked AutoEncoder (MAE) for feature pre-training can further unleash the potential of ViT on various…
Long-term activity forecasting is an especially challenging research problem because it requires understanding the temporal relationships between observed actions, as well as the variability and complexity of human activities. Despite…
Recently, masked image modeling (MIM) has become a promising direction for visual pre-training. In the context of vision transformers, MIM learns effective visual representation by aligning the token-level features with a pre-defined space…
3D object representation learning is a fundamental challenge in computer vision to infer about the 3D world. Recent advances in deep learning have shown their efficiency in 3D object recognition, among which view-based methods have…
Videos captured from multiple viewpoints can help in perceiving the 3D structure of the world and benefit computer vision tasks such as action recognition, tracking, etc. In this paper, we present a method for self-supervised learning from…
Robotic manipulation requires understanding both the 3D spatial structure of the environment and its temporal evolution, yet most existing policies overlook one or both. They typically rely on 2D visual observations and backbones pretrained…
Recently, self-supervised pre-training has advanced Vision Transformers on various tasks w.r.t. different data modalities, e.g., image and 3D point cloud data. In this paper, we explore this learning paradigm for 3D mesh data analysis based…
Masked Autoencoders (MAEs) have been shown to be effective in pre-training Vision Transformers (ViTs) for natural and medical image analysis problems. By reconstructing missing pixel/voxel information in visible patches, a ViT encoder can…
Medical vision-and-language pre-training provides a feasible solution to extract effective vision-and-language representations from medical images and texts. However, few studies have been dedicated to this field to facilitate medical…
Deploying visual reinforcement learning (RL) policies in real-world manipulation is often hindered by camera viewpoint changes. A policy trained from a fixed front-facing camera may fail when the camera is shifted -- an unavoidable…
We present EmbodiedMAE, a unified 3D multi-modal representation for robot manipulation. Current approaches suffer from significant domain gaps between training datasets and robot manipulation tasks, while also lacking model architectures…
Existing LiDAR-based 3D object detection methods for autonomous driving scenarios mainly adopt the training-from-scratch paradigm. Unfortunately, this paradigm heavily relies on large-scale labeled data, whose collection can be expensive…