Lidars　and　cameras　are　critical　sensors　that　provide　complementary　information　for　3D　detection　in　autonomous　driving.　In　recent　years,　the　emergence　of　pseudo　point　clouds　has　led　to　an　increasing　number　of　3D　object　detection　tasks　introducing　this　modality,　but　not　every　point　in　the　pseudo　point　cloud　generated　by　depth　completion　is　reliable.　In　order　to　better　utilize　pseudo　point　clouds　in　3D　object　detection　tasks　based　on　point　cloud　image　fusion,　we　propose　the　EppNet　framework　in　this　paper,　which　enables　the　network　to　learn　the　anti　noise　features　of　pseudo　point　clouds.　In　this　framework,　we　use　VoxelNet　[1]　and　VirConv　Net　[2]　to　extract　features　from　point　clouds　and　pseudo　point　clouds,　respectively.　Besides,　we　utilize　a　attentive　RoI　fusion　strategy　to　make　fuller　use　of　information　from　different　types　of　point　clouds.　Extensive　experiments　on　KITTI,　a　benchmark　for　real-world　traffic　object　identification,　revealed　that　EppNet　is　able　to　perform　favorably　in　comparison　to　earlier,　well-respected　detectors.　©　2024　IEEE.