Related papers: Efficient Self-Supervised Neuro-Analytic Visual Se…
Unsupervised learning poses one of the most difficult challenges in computer vision today. The task has an immense practical value with many applications in artificial intelligence and emerging technologies, as large quantities of unlabeled…
Does multi-view demonstration truly improve robot manipulation, or merely enhance cross-view robustness? We present a systematic study quantifying the performance gains, scaling behavior, and underlying mechanisms of multi-view data for…
Recently, self-supervised learning methods like MoCo, SimCLR, BYOL and SwAV have reduced the gap with supervised methods. These results have been achieved in a control environment, that is the highly curated ImageNet dataset. However, the…
Rotation equivariance is a desirable property in many practical applications such as motion forecasting and 3D perception, where it can offer benefits like sample efficiency, better generalization, and robustness to input perturbations.…
A robot that learns from demonstrations should not just imitate what it sees -- it should understand the high-level concepts that are being demonstrated and generalize them to new tasks. Bilevel planning is a hierarchical model-based…
Monocular visual-inertial odometry (VIO) is a critical problem in robotics and autonomous driving. Traditional methods solve this problem based on filtering or optimization. While being fully interpretable, they rely on manual interference…
Novel-view synthesis (NVS) can be tackled through different approaches, depending on the general setting: a single source image to a short video sequence, exact or noisy camera pose information, 3D-based information such as point clouds…
Weakly supervised video object segmentation (WSVOS) enables the identification of segmentation maps without requiring an extensive training dataset of object masks, relying instead on coarse video labels indicating object presence. Current…
Vision-based control systems, such as image-based visual servoing (IBVS), have been extensively explored for precise robot manipulation. A persistent challenge, however, is maintaining robust target tracking under partial or full…
Bird's-eye-view (BEV) representations derived from multi-camera input have become a central interface for online high-definition (HD) map construction. However, most approaches rely solely on ego-centric supervision, requiring large-scale…
Planning at a higher level of abstraction instead of low level torques improves the sample efficiency in reinforcement learning, and computational efficiency in classical planning. We propose a method to learn such hierarchical…
A safe and robust on-road navigation system is a crucial component of achieving fully automated vehicles. NVIDIA recently proposed an End-to-End algorithm that can directly learn steering commands from raw pixels of a front camera by using…
At the core of self-supervised learning for vision is the idea of learning invariant or equivariant representations with respect to a set of data transformations. This approach, however, introduces strong inductive biases, which can render…
The perception system is a a critical role of an autonomous driving system for ensuring safety. The driving scene perception system fundamentally represents an object detection task that requires achieving a balance between accuracy and…
This paper reports on the development, execution, and open-sourcing of a new robotics course at MIT. The course is a modern take on "Visual Navigation for Autonomous Vehicles" (VNAV) and targets first-year graduate students and senior…
In real world scenarios, due to environmental or hardware constraints, the quadrotor is forced to navigate in pure inertial navigation mode while operating indoors or outdoors. To mitigate inertial drift, end-to-end neural network…
As the first diagnostic imaging modality of avascular necrosis of the femoral head (AVNFH), accurately staging AVNFH from a plain radiograph is critical yet challenging for orthopedists. Thus, we propose a deep learning-based AVNFH…
Robot-assisted endovascular intervention offers a safe and effective solution for remote catheter manipulation, reducing radiation exposure while enabling precise navigation. Reinforcement learning (RL) has recently emerged as a promising…
Diffusion models have advanced from text-to-image (T2I) to image-to-image (I2I) generation by incorporating structured inputs such as depth maps, enabling fine-grained spatial control. However, existing methods either train separate models…
Is a deep learning model capable of understanding systems governed by certain first principle laws by only observing the system's output? Can deep learning learn the underlying physics and honor the physics when making predictions? The…