20 accepted papers
"Recently, 3D Gaussian splatting (3D-GS) has gained popularity in novel-view scene synthesis. It addresses the challenges of lengthy training times and slow rendering speeds associated with Neural Radiance Fields (NeRFs). Through rapid, differentiable rasterization of 3D Gaussians, 3D-GS achieves re…
This paper builds upon the well-established ML-based grasping technique, known as the Grasp-Rectangle (GR) method. The original GR method made two simplifying assumptions: it was designed exclusively for two-finger grippers, and it assumed that the gripper would approach objects solely from a top-do…
"Generative models are now widely used by graphic designers and artists. Prior works have shown that these models remember and often replicate content from their training data during generation. Hence as their proliferation increases, it has become important to perform a database search to determine…
"Neural Radiance Fields (NeRFs) have revolutionized the reconstruction of static scenes and objects in 3D, offering unprecedented quality. However, extending NeRFs to model dynamic objects or object articulations remains a challenging problem. Previous works have tackled this issue by focusing on pa…
"We present a simple self-supervised method to enhance the performance of ViT features for dense downstream tasks. Our Lightweight Feature Transform (LiFT) is a straightforward and compact postprocessing network that can be applied to enhance the features of any pre-trained ViT backbone. LiFT is fas…
In the pursuit of object retrieval using an aerial manipulator, developing robust visual servoing techniques in the presence of projection and motion model uncertainties is paramount. This paper proposes a novel approach to conducting image-space planning within the controllable-space of the aerial…
We present a method for joint alignment of sparse in-the-wild image collections of an object category. Most prior works assume either ground-truth keypoint annotations or a large dataset of images of a single object category. However, neither of the above assumptions hold true for the long-tail of t…
Recognizing and generating object-state compositions has been a challenging task, especially when generalizing to unseen compositions. In this paper, we study the task of cutting objects in different styles and the resulting object state changes. We propose a new benchmark suite Chop & Learn, to acc…
We introduce LilNetX, an end-to-end trainable technique for neural networks that enables learning models with specified accuracy-rate-computation trade-off. Prior works approach these problems one at a time and often require post-processing or multistage training which become less practical and do n…
Implicit Neural Representations (INR) or neural fields have emerged as a popular framework to encode multimedia signals such as images and radiance fields while retaining high-quality. Recently, learnable feature grids such as Instant-NGP have allowed significant speed-up in the training as well as…
Vision Transformers (ViTs) have gained significant popularity in recent years and have proliferated into many applications. However, their behavior under different learning paradigms is not well explored. We compare ViTs trained through different methods of supervision, and show that they learn a di…
"We present Neural Space-filling Curves (SFCs), a data-driven approach to infer a context-based scan order for a set of images. Linear ordering of pixels forms the basis for many applications such as video scrambling, compression, and auto-regressive models that are used in generative modeling for i…
The past decade has amply demonstrated the remarkable functionality that can be realized by learning complex input/output relationships. Algorithmically, one of the most important and opaque relationships is that between a problem's structure and an effective solution method. Here, we quantitatively…
We address the problem of scene layout generation for diverse domains such as images, mobile applications, documents, and 3D objects. Most complex scenes, natural or human-designed, can be expressed as a meaningful arrangement of simpler compositional graphical primitives. Generating a new layout or…
We study a referential game (a type of signaling game) where two agents communicate with each other via a discrete bottleneck to achieve a common goal. In our referential game, the goal of the speaker is to compose a message or a symbolic representation of "important" image patches, while the task f…
Recognition tasks, such as object recognition and keypoint estimation, have seen widespread adoption in recent years. Most state-of-the-art methods for these tasks use deep networks that are computationally expensive and have huge memory footprints. This makes it exceedingly difficult to deploy thes…
This letter presents the Observation-based Least-Restrictive Collision Avoidance Module (OLR-CAM) that can be added to any autonomous robot working in a shared environment and provide a high-level safety layer to the existing policy for each robot. The OLR-CAM takes raw sensory observations as input
Unsupervised representation learning holds the promise of exploiting large amounts of unlabeled data to learn general representations. A promising technique for unsupervised learning is the framework of Variational Auto-encoders (VAEs). However, unsupervised representations learned by VAEs are signi…
We present an integrated grasping system for a mobile manipulator to grasp an unknown object of interest (OI) in an unknown environment. The system autonomously scans its environment, models the OI, plans and executes a grasp, while taking into account base pose uncertainty. Due to inherent line of…
We present a localization aware efficient sampling strategy for sampling-based motion planning under uncertainty that uses a new notion of localization ability of a sample. It puts more samples in regions where sensor data is able to achieve higher uncertainty reduction while maintaining adequate sa…