45 citations · 103 across the 13 of their papers we have counts for
19 papers
CoPE-VideoLM: Leveraging Codec Primitives For Efficient Video Language Modeling
Sayan Deb Sarkar, Rémi Pautrat, Ondrej Miksik +4
Video Language Models (VideoLMs) enable AI systems to understand temporal dynamics in videos. To fit within the maximum context window constraint, current methods use keyframe samp…
UnLoc: Leveraging Depth Uncertainties for Floorplan Localization
Matthias Wüest, Francis Engelmann, Ondrej Miksik +2
We propose UnLoc, an efficient data-driven solution for sequential camera localization within floorplans. Floorplan data is readily available, long-term persistent, and robust to c…
CrossOver: 3D Scene Cross-Modal Alignment
Sayan Deb Sarkar, Ondrej Miksik, Marc Pollefeys +2
Multi-modal 3D object understanding has gained significant attention, yet current approaches often assume complete data availability and rigid alignment across all modalities. We p…
Robustness Analysis on Foundational Segmentation Models
Madeline Chantry Schiappa, Shehreen Azad, Sachidanand VS +4
Due to the increase in computational resources and accessibility of data, an increase in large, deep learning models trained on copious amounts of multi-modal data using self-super…
SGAligner : 3D Scene Alignment with Scene Graphs
Sayan Deb Sarkar, Ondrej Miksik, Marc Pollefeys +2
Building 3D scene graphs has recently emerged as a topic in scene representation for several embodied AI applications to represent the world in a structured and rich manner. With t…
LaMAR: Benchmarking Localization and Mapping for Augmented Reality
Paul-Edouard Sarlin, Mihai Dusmanu, Johannes L. Schönberger +5
Localization and mapping is the foundational technology for augmented reality (AR) that enables sharing and persistence of digital content in the real world. While significant prog…
Learning to Simulate Realistic LiDARs
Benoit Guillard, Sai Vemprala, Jayesh K. Gupta +4
Simulating realistic sensors is a challenging part in data generation for autonomous systems, often involving carefully handcrafted sensor design, scene properties, and physics mod…
TASKOGRAPHY: Evaluating robot task planning over large 3D scene graphs
Christopher Agia, Krishna Murthy Jatavallabhula, Mohamed Khodeir +5
3D scene graphs (3DSGs) are an emerging description; unifying symbolic, topological, and metric scene representations. However, typical 3DSGs contain hundreds of objects and symbol…
Cross-Descriptor Visual Localization and Mapping
Mihai Dusmanu, Ondrej Miksik, Johannes L. Schönberger +1
Visual localization and mapping is the key technology underlying the majority of mixed reality and robotics systems. Most state-of-the-art approaches rely on local features to esta…
Building Proactive Voice Assistants: When and How (not) to Interact
O. Miksik, I. Munasinghe, J. Asensio-Cubero +17
Voice assistants have recently achieved remarkable commercial success. However, the current generation of these devices is typically capable of only reactive interactions. In other…
Live Reconstruction of Large-Scale Dynamic Outdoor Worlds
Ondrej Miksik, Vibhav Vineet
Standard 3D reconstruction pipelines assume stationary world, therefore suffer from `ghost artifacts' whenever dynamic objects are present in the scene. Recent approaches has start…
Static Visual Spatial Priors for DoA Estimation
Pawel Swietojanski, Ondrej Miksik
As we interact with the world, for example when we communicate with our colleagues in a large open space or meeting room, we continuously analyse the surrounding environment and, i…
DGPose: Deep Generative Models for Human Body Analysis
Rodrigo de Bem, Arnab Ghosh, Thalaiyasingam Ajanthan +4
Deep generative modelling for human body analysis is an emerging problem with many interesting applications. However, the latent space learned by such approaches is typically not i…
Real-Time Dense Stereo Matching With ELAS on FPGA Accelerated Embedded Devices
Oscar Rahnama, Duncan Frost, Ondrej Miksik +1
For many applications in low-power real-time robotics, stereo cameras are the sensors of choice for depth perception as they are typically cheaper and more versatile than their act…
On the Robustness of Semantic Segmentation Models to Adversarial Attacks
Anurag Arnab, Ondrej Miksik, Philip H. S. Torr
Deep Neural Networks (DNNs) have demonstrated exceptional performance on most recognition tasks such as image classification and segmentation. However, they have also been shown to…
ROAM: a Rich Object Appearance Model with Application to Rotoscoping
Ondrej Miksik, Juan-Manuel Pérez-Rúa, Philip H. S. Torr +1
Rotoscoping, the detailed delineation of scene elements through a video shot, is a painstaking task of tremendous importance in professional post-production pipelines. While pixel-…
Playing Doom with SLAM-Augmented Deep Reinforcement Learning
Shehroze Bhatti, Alban Desmaison, Ondrej Miksik +3
A number of recent approaches to policy learning in 2D game domains have been successful going directly from raw input images to actions. However when employed in complex 3D enviro…
Joint Object-Material Category Segmentation from Audio-Visual Cues
Anurag Arnab, Michael Sapienza, Stuart Golodetz +4
It is not always possible to recognise objects and infer material properties for a scene from visual cues alone, since objects can look visually similar whilst being made of very d…
Staple: Complementary Learners for Real-Time Tracking
Luca Bertinetto, Jack Valmadre, Stuart Golodetz +2
Correlation Filter-based trackers have recently achieved excellent performance, showing great robustness to challenging situations exhibiting motion blur and illumination changes.…