The paper "WateRF: Robust Watermarks in Radiance Fields for Protection of Copyrights" introduces an innovative watermarking method for Neural Radiance Fields (NeRF) that can be applied to both implicit and explicit NeRF representations. The method involves fine-tuning the NeRF model to embed binary messages during the rendering process, using the discrete wavelet transform (DWT) in the NeRF space. The authors adopt a deferred back-propagation technique and introduce a patch-wise loss to improve rendering quality and bit accuracy while minimizing trade-offs. The evaluation of the method is conducted in three aspects: capacity, invisibility, and robustness of the embedded watermarks in 2D-rendered images. The proposed method achieves state-of-the-art performance with faster training speed compared to existing methods. The paper also discusses the limitations and future work, including the need for more robustness against model attacks.The paper "WateRF: Robust Watermarks in Radiance Fields for Protection of Copyrights" introduces an innovative watermarking method for Neural Radiance Fields (NeRF) that can be applied to both implicit and explicit NeRF representations. The method involves fine-tuning the NeRF model to embed binary messages during the rendering process, using the discrete wavelet transform (DWT) in the NeRF space. The authors adopt a deferred back-propagation technique and introduce a patch-wise loss to improve rendering quality and bit accuracy while minimizing trade-offs. The evaluation of the method is conducted in three aspects: capacity, invisibility, and robustness of the embedded watermarks in 2D-rendered images. The proposed method achieves state-of-the-art performance with faster training speed compared to existing methods. The paper also discusses the limitations and future work, including the need for more robustness against model attacks.