Related papers: SPARK: Sim-ready Part-level Articulated Reconstruc…

This work addresses the problem of recovering complete, simulatable object geometry from reconstructed real-world scenes, enabling physics-based interaction with objects embedded in the scene. While modern multi-view reconstruction methods…

Simultaneous Localization and Mapping (SLAM) plays an important role in many robotics fields, including social robots. Many of the available visual SLAM methods are based on the assumption of a static world and struggle in dynamic…

Personalized search demands the ability to model users' evolving, multi-dimensional information needs; a challenge for systems constrained by static profiles or monolithic retrieval pipelines. We present SPARK (Search Personalization via…

Robots operating in unstructured environments often require accurate and consistent object-level representations. This typically requires segmenting individual objects from the robot's surroundings. While recent large models such as Segment…

A bottleneck in learning to understand articulated 3D objects is the lack of large and diverse datasets. In this paper, we propose to leverage large language models (LLMs) to close this gap and generate articulated assets at scale. We…

Retargeting motion between characters with different skeleton structures is a fundamental challenge in computer animation. When source and target characters have vastly different bone arrangements, maintaining the original motion's…

We present a neural-field-based large-scale reconstruction system that fuses lidar and vision data to generate high-quality reconstructions that are geometrically accurate and capture photo-realistic textures. This system adapts the…

We present a technique for simultaneous 3D reconstruction of static regions and rigidly moving objects in a scene. An RGB-D frame is represented as a collection of features, which are points and planes. We classify the features into static…

This work presents a novel RGB-D SLAM approach to simultaneously segment, track and reconstruct the static background and large dynamic rigid objects that can occlude major portions of the camera view. Previous approaches treat dynamic…

Temporal Knowledge Graph (TKG) forecasting is crucial for predicting future events using historical data. With the surge of Large Language Models (LLMs), recent studies have begun exploring their integration into TKG forecasting and…

In this paper, we propose a novel method for joint recovery of camera pose, object geometry and spatially-varying Bidirectional Reflectance Distribution Function (svBRDF) of 3D scenes that exceed object-scale and hence cannot be captured…

Open-world 3D generation has recently attracted considerable attention. While many single-image-to-3D methods have yielded visually appealing outcomes, they often lack sufficient controllability and tend to produce hallucinated regions that…

Robot planning in partially observable domains is difficult, because a robot needs to estimate the current state and plan actions at the same time. When the domain includes many objects, reasoning about the objects and their relationships…

We introduce an active 3D reconstruction method which integrates visual perception, robot-object interaction, and 3D scanning to recover both the exterior and interior, i.e., unexposed, geometries of a target 3D object. Unlike other works…

We present a framework for visual action planning of complex manipulation tasks with high-dimensional state spaces, focusing on manipulation of deformable objects. We propose a Latent Space Roadmap (LSR) for task planning which is a…

The majority of approaches for acquiring dense 3D environment maps with RGB-D cameras assumes static environments or rejects moving objects as outliers. The representation and tracking of moving objects, however, has significant potential…

Vision-Language Model (VLM) is an important component to enable robust robot manipulation. Yet, using it to translate human instructions into an action-resolvable intermediate representation often needs a tradeoff between…

This document presents PLVS: a real-time system that leverages sparse SLAM, volumetric mapping, and 3D unsupervised incremental segmentation. PLVS stands for Points, Lines, Volumetric mapping, and Segmentation. It supports RGB-D and Stereo…

Constructing and animating humans is an important component for building virtual worlds in a wide variety of applications such as virtual reality or robotics testing in simulation. As there are exponentially many variations of humans with…

Aerial robots play a vital role in various applications where the situational awareness of the robots concerning the environment is a fundamental demand. As one such use case, drones in GPS-denied environments require equipping with…