Jonathon Luiten
YOU?
Author Swipe
View article: SplaTAM: Splat, Track & Map 3D Gaussians for Dense RGB-D SLAM
SplaTAM: Splat, Track & Map 3D Gaussians for Dense RGB-D SLAM Open
Dense simultaneous localization and mapping (SLAM) is crucial for robotics and augmented reality applications. However, current methods are often hampered by the non-volumetric or implicit way they represent a scene. This work introduces S…
View article: Dynamic 3D Gaussians: Tracking by Persistent Dynamic View Synthesis
Dynamic 3D Gaussians: Tracking by Persistent Dynamic View Synthesis Open
We present a method that simultaneously addresses the tasks of dynamic scene novel-view synthesis and six degree-of-freedom (6-DOF) tracking of all dense scene elements. We follow an analysis-by-synthesis framework, inspired by recent work…
View article: TarViS: A Unified Approach for Target-based Video Segmentation
TarViS: A Unified Approach for Target-based Video Segmentation Open
The general domain of video segmentation is currently fragmented into different tasks spanning multiple benchmarks. Despite rapid progress in the state-of-the-art, current methods are overwhelmingly task-specific and cannot conceptually ge…
View article: BURST: A Benchmark for Unifying Object Recognition, Segmentation and Tracking in Video
BURST: A Benchmark for Unifying Object Recognition, Segmentation and Tracking in Video Open
Multiple existing benchmarks involve tracking and segmenting objects in video e.g., Video Object Segmentation (VOS) and Multi-Object Tracking and Segmentation (MOTS), but there is little interaction between them due to the use of disparate…
View article: Differentiable Soft-Masked Attention
Differentiable Soft-Masked Attention Open
Transformers have become prevalent in computer vision due to their performance and flexibility in modelling complex operations. Of particular significance is the 'cross-attention' operation, which allows a vector representation (e.g. of an…
View article: Forecasting from LiDAR via Future Object Detection
Forecasting from LiDAR via Future Object Detection Open
Object detection and forecasting are fundamental components of embodied perception. These two problems, however, are largely studied in isolation by the community. In this paper, we propose an end-to-end approach for detection and motion f…
View article: HODOR: High-level Object Descriptors for Object Re-segmentation in Video Learned from Static Images
HODOR: High-level Object Descriptors for Object Re-segmentation in Video Learned from Static Images Open
Existing state-of-the-art methods for Video Object Segmentation (VOS) learn low-level pixel-to-pixel correspondences between frames to propagate object masks across video. This requires a large amount of densely annotated video data, which…
View article: The Ninth Visual Object Tracking VOT2021 Challenge Results
The Ninth Visual Object Tracking VOT2021 Challenge Results Open
The Visual Object Tracking challenge VOT2021 is the ninth annual tracker benchmarking activity organized by the VOT initiative. Results of 71 trackers are presented; many are state-of-the-art trackers published at major computer vision con…
View article: Opening up Open-World Tracking
Opening up Open-World Tracking Open
Tracking and detecting any object, including ones never-seen-before during model training, is a crucial but elusive capability of autonomous systems. An autonomous agent that is blind to never-seen-before objects poses a safety hazard when…
View article: Single-Shot Panoptic Segmentation
Single-Shot Panoptic Segmentation Open
We present a novel end-to-end single-shot method that segments countable object instances (things) as well as background regions (stuff) into a non-overlapping panoptic segmentation at almost video frame rate. Current state-of-the-art meth…
View article: Siam R-CNN: Visual Tracking by Re-Detection
Siam R-CNN: Visual Tracking by Re-Detection Open
We present Siam R-CNN, a Siamese re-detection architecture which unleashes the full power of two-stage object detection approaches for visual object tracking. We combine this with a novel tracklet-based dynamic programming algorithm, which…
View article: 4D Generic Video Object Proposals
4D Generic Video Object Proposals Open
Many high-level video understanding methods require input in the form of object proposals. Currently, such proposals are predominantly generated with the help of networks that were trained for detecting and segmenting a set of known object…
View article: UnOVOST: Unsupervised Offline Video Object Segmentation and Tracking
UnOVOST: Unsupervised Offline Video Object Segmentation and Tracking Open
We address Unsupervised Video Object Segmentation (UVOS), the task of automatically generating accurate pixel masks for salient objects in a video sequence and of tracking these objects consistently through time, without any input about wh…
View article: Track to Reconstruct and Reconstruct to Track
Track to Reconstruct and Reconstruct to Track Open
Object tracking and 3D reconstruction are often performed together, with tracking used as input for reconstruction. However, the obtained reconstructions also provide useful information for improving tracking. We propose a novel method tha…
View article: MOTS: Multi-Object Tracking and Segmentation
MOTS: Multi-Object Tracking and Segmentation Open
This paper extends the popular task of multi-object tracking to multi-object tracking and segmentation (MOTS). Towards this goal, we create dense pixel-level annotations for two existing tracking datasets using a semi-automatic annotation …
View article: Large-Scale Object Mining for Object Discovery from Unlabeled Video
Large-Scale Object Mining for Object Discovery from Unlabeled Video Open
This paper addresses the problem of object discovery from unlabeled driving videos captured in a realistic automotive setting. Identifying recurring object categories in such raw video streams is a very challenging problem. Not only do obj…
View article: BoLTVOS: Box-Level Tracking for Video Object Segmentation
BoLTVOS: Box-Level Tracking for Video Object Segmentation Open
We approach video object segmentation (VOS) by splitting the task into two sub-tasks: bounding box level tracking, followed by bounding box segmentation. Following this paradigm, we present BoLTVOS (Box-Level Tracking for VOS), which consi…
View article: Towards Large-Scale Video Video Object Mining
Towards Large-Scale Video Video Object Mining Open
We propose to leverage a generic object tracker in order to perform object mining in large-scale unlabeled videos, captured in a realistic automotive setting. We present a dataset of more than 360'000 automatically mined object tracks from…
View article: Large-Scale Object Discovery and Detector Adaptation from Unlabeled Video
Large-Scale Object Discovery and Detector Adaptation from Unlabeled Video Open
We explore object discovery and detector adaptation based on unlabeled video sequences captured from a mobile platform. We propose a fully automatic approach for object mining from video which builds upon a generic object tracking approach…