Enhanced NeRF on heavy occluded conditions for crops

Based on the benchmarked classical structure-from-motion pipeline and neural radiance fields (NeRF) variants for this field, We strived to devise an enhanced NeRF, one that incorporated cross-view feature correlation and geometric priors on leaves and fruits to achieve high-fidelity reconstruction in real world experiments for heavy occluded conditions. In doing so, the resulting 3D models successfully supported downstream applications in phenotype estimation and crop-quality prediction accomplishments in real world scenarios.

During internship as a researcher at SenseTime Inc.