KITTI
Canonical43papers using it
1,294HF downloads
5HF likes
2016first seen
Dataset Card for Kitti The Kitti dataset. The Kitti object detection and object orientation estimation benchmark consists of 7481 training images and 7518 test images, comprising a total of 80.256 labeled objects
🤗 Hugging Face⚖ unknown
Papers using KITTI (35)
- Tracking Objects As PointsObjects Are Different: Flexible Monocular 3D Object DetectionUnsupervised Scale-consistent Depth And Ego-motion Learning From Monocular VideoVoxel Field Fusion For 3D Object DetectionWeb Stereo Video Supervision For Depth Prediction From Dynamic ScenesM3DSSD: Monocular 3D Single Stage Object DetectorTJU-DHD: A Diverse High-resolution Dataset For Object Detection3D Object Detection Using Scale Invariant And Feature Reweighting NetworksTiny-dsod: Lightweight Object Detection For Resource-restricted UsagesSa-det3d: Self-attention Based Context-aware 3D Object DetectionDepth From Videos In The Wild: Unsupervised Monocular Depth Learning From Unknown CamerasDeeppruner: Learning Efficient Stereo Matching Via Differentiable PatchmatchTowards Real-time Unsupervised Monocular Depth Estimation On CPUDomain Adaptive YOLO For One-stage Cross-domain DetectionInstance Segmentation With Point SupervisionDBQ-SSD: Dynamic Ball Query For Efficient 3D Object DetectionEnd-to-End Instance Segmentation with Recurrent AttentionNvs-monodepth: Improving Monocular Depth Prediction With Novel View SynthesisSelf-supervised Object Detection Via Generative Image SynthesisNovel View Synthesis For Large-scale Scene Using Adversarial LossRe-ranking Object Proposals For Object Detection In Automatic DrivingFutureDepth: Learning to Predict the Future Improves Video Depth
EstimationLearning to Separate: Detecting Heavily-Occluded Objects in Urban ScenesSem-lsd: A Learning-based Semantic Line Segment DetectorSAMPLING: Scene-adaptive Hierarchical Multiplane Images Representation For Novel View Synthesis From A Single ImageTracking Objects as Pixel-wise DistributionsDetail Preserving Residual Feature Pyramid Modules For Optical FlowSelf-supervised Monocular Depth Estimation with Large Kernel AttentionMono3DV: Monocular 3D Object Detection with 3D-Aware Bipartite Matching and Variational Query DeNoisingSENSE: Stereo OpEN Vocabulary SEmantic SegmentationMultiscale Video Transformers For Class Agnostic Segmentation In Autonomous DrivingRecursive Cross-view: Use Only 2D Detectors To Achieve 3D Object Detection Without 3D AnnotationsAdjacent-view Transformers For Supervised Surround-view Depth EstimationHmaflow: Learning More Accurate Optical Flow Via Hierarchical Motion Field AlignmentSqldepth: Generalizable Self-supervised Fine-structured Monocular Depth Estimation