LZleejean

Results 10 issues of LZleejean

There are depth output and semantation output. In the paper, the method also outputs plane parameters and 3D mesh models. Is this because these outputs are disabled in the predict.py...

The paper demonstrate the proposed method for multi tasks, e.g. Gigapixel image, SDF, NeRF, Neural radiance caching. The example code of some tasks except for nrc are included in this...

I found that it is commented and does not compile successful when uncommented.

I install the redner via pip on linux. When I run the test scripts, e.g. 'tests/test_g_buffer.py', the error occurs. `python: /tmp/pip-req-build-k_hkhooj/src/scene.cpp:125: Scene::Scene(const Camera&, const std::vector&, const std::vector&, const std::vector&, const...

The point light only available in the defered rendering mode and this mode assume Lambertian shading and does not compute shadow. I think supporting the point light in the pathtracing...

Thanks for your inspired work. I have finished the training of whole framework. I want to evaluate the model for reproducing the quantitative results reported in paper. Could you provide...

Hi, is it differentiable?

Great Work. The paper shows some results in the dataset proposed in VR-NeRF. However, the training scripts are not found in the repo. Could you provide the loading code or...

I want to use your renderer, and do you provide a scene to be rendered, which is suitable for your API?

**Is your feature request related to a problem? Yes.** Excellent works. We train the model on seveal data with nerfstudio and get good resutls. But I'm confused at the quantitative...