• The vision chip integrates a 2D/3D image sensor with a programmable visual processor using organic substrate 3D packaging, enabling compact end-to-end visual SoC.
• A novel on-chip processing flow with die-to-die image transmission and low-latency fixed-point processing supports real-time CNNs and conventional algorithms.
• The end-to-end 2D/3D vision system achieves real-time applications: face detection with 10.2 ms delay and depth map reconstruction with 4.1 ms delay.
• The system maintains a frame rate exceeding 30 fps for image acquisition, processing, and display, demonstrating practical viability.