KITTI

'We restore paintings to their former glory'

'We restore paintings to their former glory' Visiting stately homes or art galleries, the paintings offer a glimpse into the past; how people dressed, what a place looked like, what myths or fables inspired art. What also might strike you is, after centuries on display, how can some remain in such good condition, the colours still bright, the details clear and defined? For a vast swathe of paintings in venues across Yorkshire, the answers lies in a Sheffield studio, where old artwork is...

FlowIt: Global Matching via Hierarchical Transformers and Optimal Transport for Optical Flow

arXiv:2603.28759v2 Announce Type: replace Abstract: We present FlowIt, a novel architecture for optical flow estimation that combines global matching with confidence and occlusion-guided refinement. At its core, FlowIt leverages a hierarchical transformer architecture that captures extensive global context, enabling the model to effectively model long-range correspondences. To overcome the limitations of localized matching, we formulate the flow initialization as an optimal transport problem.

Joint Multi-Camera LiDAR Extrinsic Calibration via Learned Pairwise Initialization and Geometric Refinement

arXiv:2605.31576v1 Announce Type: new Abstract: Most learning-based camera-LiDAR calibration methods treat each camera-LiDAR pair independently, ignoring the rigid geometric coupling in multi-camera platforms. As a result, per-camera estimates may be individually accurate yet inconsistent at the system level. We present a two-stage framework for joint multi-camera LiDAR extrinsic calibration that combines learned pairwise matching with geometric refinement.

Geometry-Aware Fisheye-LiDAR Fusion for Robust 3D Object Detection in Low-Overlap Setups

Announce Type: new Abstract: As autonomous systems expand from capital-intensive robotaxis to cost-sensitive logistics, sensor configurations are increasingly optimized for coverage-per-cost. A prevalent sparse-view setup utilizes dual-fisheye cameras with a roof-mounted LiDAR, introducing severe geometric challenges: extreme radial distortion, minimal overlap, and misalignment between spherical projections and rectilinear grids. BEV fusion algorithms typically force image and point cloud...

Mina the Hollower, a Sims alternative and other new indie games worth checking out

Mina the Hollower, a Sims alternative and other new indie games worth checking out Plus, a whole bunch of games that'll give your brain a workout. Welcome to our latest roundup of what's going on in the indie game space. We're here to tell you about a bunch of new games you can dive into this weekend.

A Book I Wish I’d Read at 22

BEV-ODOM2: Enhanced BEV-based Monocular Visual Odometry with PV-BEV Fusion and Dense Flow Supervision for Ground Robots

Announce Type: replace Abstract: Scale-consistent ego-motion estimation is fundamental for autonomous ground robots. Bird's-Eye-View (BEV) representation naturally addresses the scale drift problem of monocular visual odometry (MVO) by providing a metric-scaled planar workspace, enabling the simplification of 6-DoF ego-motion to a more robust 3-DoF model. However, existing BEV-based methods suffer from two key limitations: sparse supervision signals from pose-only training, and information...

Distortion-Aware PETR for BEV Object Detection with Mixed Pinhole-Fisheye Cameras

arXiv:2606.08680v1 Announce Type: new Abstract: Fisheye cameras are widely deployed in autonomous driving perception suites for their low cost and full-coverage field of view (FOV), yet their potential remains underleveraged in 3D object detection. Severe radial distortion challenges most BEV detectors by violating the fundamental assumption of uniform sampling.

Zero-Shot Polygon Matching with Pre-trained Models for Pose Estimation and Polygon Cloud from Challenging Stereo

Announce Type: replace Abstract: While stereo matching has achieved maturity for 0D point and 1D line primitives, establishing correspondences for 2D polygons remains largely unexplored due to challenges including disparity discontinuity, scale variation, training dependency, and poor generalization, limiting downstream tasks such as pose estimation and 3D reconstruction. To address these issues, we are the first to propose a Zero-shot Polygon Matching paradigm with Pre-trained Models (i.e.,...

All the Summer Game Fest showcases you can catch today

All the Summer Game Fest showcases you can catch today You can get the latest about wholesome, story-rich and LGBTQ+ games from today's streams. The 2026 Summer Game Fest main show and Day of the Devs have already brought us launch announcements for Final Fantasy 7 Revelation, the Resident Evil: Code Veronica remake and Virtua Fighter Crossroads, as well as other news about highly anticipated games. But the event is far from over: Today, June 6, you can catch more showcases featuring games...