Due to policy support, low cost and easy applicability, distribution photovoltaic systems (DPVSs) are increasingly popular among residential community. However, small-scale DPVSs of less than 10 kWp are always installed behind the meter (BTM), without metering the photovoltaic (PV) power generation separately, which results in the invisible of the PV power generation. Only access of net load data can result in non-optimal distribution network control and optimization, leading to a series of energy management problems. In order to solve the aforementioned problems, this paper proposes a BTM net load disaggregation method focusing on small-scale DPVSs, with only net load data of residential users in a community, without relying on weather data and models assumption. Considering that community users’ DPVSs usually exhibit approximate output characteristics, neighboring net load is used to extract PV power generation information as mutual proxies. After obtaining approximate PV proxy data by subtracting composite power of inter-users, Maximal Information Coefficient (MIC) is performed to obtain final PV power generation disaggregation results. Testing results show that the proposed method achieves considerable disaggregation accuracy in the absence of weather data.