Latest

• MonoLayout: Amodal scene layout from a single image
• INFER: INtermediate representations for FuturE pRediction
• CalibNet: Self-Supervised Extrinsic Calibration using 3D Spatial Transformer Networks
• Geometric Consistency for Self-Supervised End-to-End Visual Odometry
• The Earth ain’t Flat: Monocular Reconstruction of Vehicles on Steep and Graded Roads from a Moving Camera
• Beyond Pixels: Leveraging Geometry and Shape Cues for Multi-Object Tracking
• Constructing Category-Specific Models for Monocular Object SLAM
• Shape Priors for Real-Time Monocular Object Localization in Dynamic Environments
• Reconstructing Vehicles From a Single Image: Shape Priors for Road Scene Understanding