The　most　negative　effects　caused　by　earthquakes　are　the　damage　and　collapse　of　buildings.　Seismic　building　retrofitting　and　repair　can　effectively　reduce　the　negative　impact　on　post-earthquake　buildings.　The　priority　to　repair　the　construction　after　being　damaged　by　an　earthquake　is　to　perform　an　assessment　of　seismic　buildings.　The　traditional　damage　assessment　method　is　mainly　based　on　visual　inspection,　which　is　highly　subjective　and　has　low　efficiency.　To　improve　the　intelligence　of　damage　assessments　for　post-earthquake　buildings,　this　paper　proposed　an　assessment　method　using　CV　(Computer　Vision)　and　AR　(Augmented　Reality).　Firstly,　this　paper　proposed　a　fusion　mechanism　for　the　CV　and　AR　of　the　assessment　method.　Secondly,　the　CNN　(Convolutional　Neural　Network)　algorithm　and　gray　value　theory　are　used　to　determine　the　damage　information　of　post-earthquake　buildings.　Then,　the　damage　assessment　can　be　visually　displayed　according　to　the　damage　information.　Finally,　this　paper　used　a　damage　assessment　case　of　seismic-reinforced　concrete　frame　beams　to　verify　the　feasibility　and　effectiveness　of　the　proposed　assessment　method.