Zipeng WANG

> You can read their follow-up work [mip-nerf](https://jonbarron.info/mipnerf/) where only one network is used. It performs even better than nerf. Thank you for your quick reply. Mip-NeRF states that >...

Thanks for your detailed reply. May I ask which specific method do you use to generate optical flow to derive the results in the paper (Tab.1 and Tab.3)? Do you...

Thanks a lot for you reply.

Update: Hi, I have tried to estimate optical flows using the pretrained [EvFlowNet](https://surfdrive.surf.nl/files/index.php/s/sv36q8ZTqVZuWl9?path=%2Ftrained_models%2FEVFlowNet_E2VID) as in [ssl-e2vid](https://github.com/tudelft/ssl_e2vid). However the results are not very satifactory. Here are some results I reproduced on...