15 citations · 30 across the 12 of their papers we have counts for
14 papers
VidAct: Learning Manipulation from In-the-Wild Videos with Object-Centric 3D Awareness
Hang Li, Mingxin Zhang, Zihan Wu +9
Video demonstrations offer a scalable alternative to costly robot data for learning manipulation, yet existing reconstruction-based approaches often rely on constrained camera view…
Rethinking 3D Noise: Learning 3D-Aware Video Priors via Optimization-Free Morphological Perturbations
Onat Şahin, Mohammad Altillawi, George Eskandar +2
3D scene representations like NeRF and 3D Gaussian Splatting (3DGS) suffer severe artifacts in sparse-view settings. Recent generative 3D artifact fixers attempt to address this, b…
Orchestrating Spatial Semantics via a Zone-Graph Paradigm for Intricate Indoor Scene Generation
Meisheng Zhang, Shizhao Sun, Yang Zhao +3
Autonomous 3D indoor scene synthesis breaks down in non-convex rooms with tightly coupled spatial constraints. Data-driven generators lack topological priors for long-horizon plann…
VideoWeaver: Multimodal Multi-View Video-to-Video Transfer for Embodied Agents
George Eskandar, Fengyi Shen, Mohammad Altillawi +4
Recent progress in video-to-video (V2V) translation has enabled realistic resimulation of embodied AI demonstrations, a capability that allows pretrained robot policies to be trans…
ReMem-VLA: Empowering Vision-Language-Action Model with Memory via Dual-Level Recurrent Queries
Hang Li, Fengyi Shen, Dong Chen +6
Vision-language-action (VLA) models for closed-loop robot control are typically cast under the Markov assumption, making them prone to errors on tasks requiring historical context.…
ConfCtrl: Enabling Precise Camera Control in Video Diffusion via Confidence-Aware Interpolation
Liudi Yang, George Eskandar, Fengyi Shen +5
We address the challenge of novel view synthesis from only two input images under large viewpoint changes. Existing regression-based methods lack the capacity to reconstruct unseen…
CE-NPBG: Connectivity Enhanced Neural Point-Based Graphics for Novel View Synthesis in Autonomous Driving Scenes
Mohammad Altillawi, Fengyi Shen, Liudi Yang +2
Current point-based approaches encounter limitations in scalability and rendering quality when using large 3D point cloud maps because using them directly for novel view synthesis…
ConsistentDreamer: View-Consistent Meshes Through Balanced Multi-View Gaussian Optimization
Onat Şahin, Mohammad Altillawi, George Eskandar +2
Recent advances in diffusion models have significantly improved 3D generation, enabling the use of assets generated from an image for embodied AI simulations. However, the one-to-m…
LiDAR Loop Closure Detection using Semantic Graphs with Graph Attention Networks
Liudi Yang, Ruben Mascaro, Ignacio Alzugaray +4
In this paper, we propose a novel loop closure detection algorithm that uses graph attention neural networks to encode semantic graphs to perform place recognition and then use sem…
Lifelong 3D Mapping Framework for Hand-held & Robot-mounted LiDAR Mapping Systems
Liudi Yang, Sai Manoj Prakhya, Senhua Zhu +1
We propose a lifelong 3D mapping framework that is modular, cloud-native by design and more importantly, works for both hand-held and robot-mounted 3D LiDAR mapping systems. Our pr…
OpenSU3D: Open World 3D Scene Understanding using Foundation Models
Rafay Mohiuddin, Sai Manoj Prakhya, Fiona Collins +2
In this paper, we present a novel, scalable approach for constructing open set, instance-level 3D scene representations, advancing open world understanding of 3D environments. Exis…
Implicit Learning of Scene Geometry from Poses for Global Localization
Mohammad Altillawi, Shile Li, Sai Manoj Prakhya +2
Global visual localization estimates the absolute pose of a camera using a single image, in a previously mapped area. Obtaining the pose from a single image enables many robotics a…
Global Localization: Utilizing Relative Spatio-Temporal Geometric Constraints from Adjacent and Distant Cameras
Mohammad Altillawi, Zador Pataki, Shile Li +1
Re-localizing a camera from a single image in a previously mapped area is vital for many computer vision applications in robotics and augmented/virtual reality. In this work, we ad…
Long-Term Invariant Local Features via Implicit Cross-Domain Correspondences
Zador Pataki, Mohammad Altillawi, Menelaos Kanakis +5
Modern learning-based visual feature extraction networks perform well in intra-domain localization, however, their performance significantly declines when image pairs are captured…