3D Computer Vision Study Plan

3D representations, coordinate systems, rigid transformations, and the foundations of spatial computing.

Pinhole camera model, lens distortion, intrinsic/extrinsic parameters, and calibration techniques.

Fundamental and essential matrices, stereo rectification, matching algorithms, and disparity estimation.

Structure from Motion, bundle adjustment, COLMAP pipelines, and multi-view reconstruction.

Monocular depth networks, multi-view stereo, active sensing with LiDAR and structured light.

Photogrammetry, mesh generation, Poisson reconstruction, signed distance functions, and texture mapping.

PointNet architectures, 3D convolutions, voxelization, segmentation, and registration with ICP.

VoxelNet, PointPillars, CenterPoint, BEV detection, sensor fusion, and evaluation.

Semantic and instance segmentation in 3D, scene graphs, occupancy networks, and indoor reconstruction.

Feature-based and direct SLAM, visual-inertial odometry, deep SLAM, relocalization, and loop closure.

Volume rendering, positional encoding, Instant-NGP, Mip-NeRF, and dynamic scene extensions.

Gaussian representation, differentiable rasterization, optimization, densification, and dynamic 4D extensions.

Text-to-3D with DreamFusion, image-to-3D reconstruction, multi-view diffusion, and 3D-aware generation.