Related papers: GenNBV: Generalizable Next-Best-View Policy for Ac…
It is a long-standing problem in robotics to develop agents capable of executing diverse manipulation tasks from visual observations in unstructured real-world environments. To achieve this goal, the robot needs to have a comprehensive…
While Neural Radiance Fields (NeRFs) have demonstrated exceptional quality, their protracted training duration remains a limitation. Generalizable and MVS-based NeRFs, although capable of mitigating training time, often incur tradeoffs in…
Landmark-based robot self-localization has recently garnered interest as a highly-compressive domain-invariant approach for performing visual place recognition (VPR) across domains (e.g., time of day, weather, and season). However,…
Training vision-based manipulation policies that are robust across diverse visual environments remains an important and unresolved challenge in robot learning. Current approaches often sidestep the problem by relying on invariant…
There remains an important need for the development of image reconstruction methods that can produce diagnostically useful images from undersampled measurements. In magnetic resonance imaging (MRI), for example, such methods can facilitate…
Novel view synthesis (NVS) enables to generate new images of a scene or convert a set of 2D images into a comprehensive 3D model. In the context of Space Domain Awareness, since space is becoming increasingly congested, NVS can accurately…
Solving image-to-3D from a single view is an ill-posed problem, and current neural reconstruction methods addressing it through diffusion models still rely on scene-specific optimization, constraining their generalization capability. To…
The development of generalizable Novel View Synthesis (NVS) models is critically limited by the scarcity of large-scale training data featuring diverse and precise camera trajectories. While real-world captures are photorealistic, they are…
Active vision is inherently attention-driven: The agent actively selects views to attend in order to fast achieve the vision task while improving its internal representation of the scene being observed. Inspired by the recent success of…
High-quality observations of the real world are crucial for a variety of applications, including producing 3D printed replicas of small-scale scenes and conducting inspections of large-scale infrastructure. These 3D observations are…
Real-time visibility determination in expansive or dynamically changing environments has long posed a significant challenge in computer graphics. Existing techniques are computationally expensive and often applied as a precomputation step…
Recent photorealistic Novel View Synthesis (NVS) advances have increasingly gained attention. However, these approaches remain constrained to small indoor scenes. While optimization-based NVS models have attempted to address this,…
Visual image reconstruction, the decoding of perceptual content from brain activity into images, has advanced significantly with the integration of deep neural networks (DNNs) and generative models. This review traces the field's evolution…
Novel view synthesis (NVS) of multi-human scenes imposes challenges due to the complex inter-human occlusions. Layered representations handle the complexities by dividing the scene into multi-layered radiance fields, however, they are…
Active object reconstruction using autonomous robots is gaining great interest. A primary goal in this task is to maximize the information of the object to be reconstructed, given limited on-board resources. Previous view planning methods…
We present RangeRCNN, a novel and effective 3D object detection framework based on the range image representation. Most existing methods are voxel-based or point-based. Though several optimizations have been introduced to ease the sparsity…
Recent advancements in radiance field rendering, exemplified by Neural Radiance Fields (NeRF) and 3D Gaussian Splatting (3DGS), have significantly progressed 3D modeling and reconstruction. The use of multiple 360-degree omnidirectional…
Imitation learning has emerged as a crucial ap proach for acquiring visuomotor skills from demonstrations, where designing effective observation encoders is essential for policy generalization. However, existing methods often struggle to…
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…
This paper presents a novel approach for sparse 3D reconstruction by leveraging the expressive power of Neural Radiance Fields (NeRFs) and fast transfer of their features to learn accurate occupancy fields. Existing 3D reconstruction…