dunbar12138 / pix2pix3D

pix2pix3D: Generating 3D Objects from 2D User Inputs
http://www.cs.cmu.edu/~pix2pix3D/
MIT License
1.65k stars 132 forks source link

Generalization of edge2car #10

Open lanchen2019 opened 1 year ago

lanchen2019 commented 1 year ago

Hi, Thanks for releasing your code and model! I tried to test new edge images but get similar results. This is the input,

edge2car2 and these are outputs

edge2car_1_label edge2car_1

The generated video cannot align well with the input edge image. The command is "python applications/generate_video.py --network checkpoints/pix2pix3d_edge2car.pkl --outdir examples --random_seed 1 --cfg edge2car --input examples/edge2car2.png". What is your suggestion for generating better results? Best Wishes

junyanz commented 1 year ago

The model is trained on mostly sedans (certainly not trucks). Training models on larger datasets or augmented data might make it work better for your input.

lanchen2019 commented 1 year ago

Thanks a lot and congratulations! Hope the training code will be released soon thus I will train on other datasets.