Related papers: Bayes3D: fast learning and inference in structured…
We introduce a framework for multi-camera 3D object detection. In contrast to existing works, which estimate 3D bounding boxes directly from monocular images or use depth prediction networks to generate input for 3D object detection from 2D…
Understanding the 3D geometry and semantics of driving scenes is critical for safe autonomous driving. Recent advances in 3D occupancy prediction have improved scene representation but often suffer from visual inconsistencies, leading to…
Estimating and understanding the surroundings of the vehicle precisely forms the basic and crucial step for the autonomous vehicle. The perception system plays a significant role in providing an accurate interpretation of a vehicle's…
3D scene understanding for robotic applications exhibits a unique set of requirements including real-time inference, object-centric latent representation learning, accurate 6D pose estimation and 3D reconstruction of objects. Current…
Recognition of occluded objects in unseen indoor environments is a challenging problem for mobile robots. This work proposes a new slicing-based topological descriptor that captures the 3D shape of object point clouds to address this…
3D reconstruction is a fundamental problem in computer vision, and the task is especially challenging when the object to reconstruct is partially or fully occluded. We introduce a method that uses the shadows cast by an unobserved object in…
Learning a physical model from video data that can comprehend physical laws and predict the future trajectories of objects is a formidable challenge in artificial intelligence. Prior approaches either leverage various Partial Differential…
3D shape is a crucial but heavily underutilized cue in today's computer vision systems, mostly due to the lack of a good generic shape representation. With the recent availability of inexpensive 2.5D depth sensors (e.g. Microsoft Kinect),…
Perceiving a three-dimensional (3D) scene with multiple objects while moving indoors is essential for vision-based mobile cobots, especially for enhancing their manipulation tasks. In this work, we present an end-to-end pipeline with…
Robust grasping is a major, and still unsolved, problem in robotics. Information about the 3D shape of an object can be obtained either from prior knowledge (e.g., accurate models of known objects or approximate models of familiar objects)…
Effective robotic manipulation relies on a precise understanding of 3D scene geometry, and one of the most straightforward ways to acquire such geometry is through multi-view observations. Motivated by this, we present GP3 -- a 3D…
This paper presents Planar Gaussian Splatting (PGS), a novel neural rendering approach to learn the 3D geometry and parse the 3D planes of a scene, directly from multiple RGB images. The PGS leverages Gaussian primitives to model the scene…
We propose UniSeg3D, a unified 3D scene understanding framework that achieves panoptic, semantic, instance, interactive, referring, and open-vocabulary segmentation tasks within a single model. Most previous 3D segmentation approaches are…
Recently, multi-view diffusion-based 3D generation methods have gained significant attention. However, these methods often suffer from shape and texture misalignment across generated multi-view images, leading to low-quality 3D generation…
3D Gaussian Splatting is renowned for its high-fidelity reconstructions and real-time novel view synthesis, yet its lack of semantic understanding limits object-level perception. In this work, we propose ObjectGS, an object-aware framework…
A natural approach to generative modeling of videos is to represent them as a composition of moving objects. Recent works model a set of 2D sprites over a slowly-varying background, but without considering the underlying 3D scene that gives…
A bathtub in a library, a sink in an office, a bed in a laundry room -- the counter-intuition suggests that scene provides important prior knowledge for 3D object detection, which instructs to eliminate the ambiguous detection of similar…
As robots increasingly integrate into everyday environments, ensuring their safe navigation around humans becomes imperative. Efficient and safe motion planning requires robots to account for human behavior, particularly in constrained…
In autonomous navigation of mobile robots, sensors suffer from massive occlusion in cluttered environments, leaving significant amount of space unknown during planning. In practice, treating the unknown space in optimistic or pessimistic…
Humans can infer the three-dimensional structure of objects from two-dimensional visual inputs. Modeling this ability has been a longstanding goal for the science and engineering of visual intelligence, yet decades of computational methods…