User:Jin Ke

From BRL-CAD
Revision as of 06:22, 23 July 2024 by Jin Ke (talk | contribs) (→‎Development Logs)
(diff) ← Older revision | Latest revision (diff) | Newer revision → (diff)

Development Logs[edit]

Community Bonding Period


Work Period

Monday, June 10th, 2024[edit]

  • Updated the CMake file to add a new project, rt_trainneural.
  • Added the file rt_trainer.cpp, which is prepared for the sampling method.

Tuesday, June 11th, 2024[edit]

  • A function was written using rt_raytrace to collect receipts with the output r,g,b

Wednesday, June 12th, 2024[edit]

  • add a_hit() and a_miss() function


Monday, June 24th, 2024[edit]

  • finish plotting points with a mged script. I create a mged automately:
in point1.s sph 1 1 1 0.1
in point2.s sph 1 2 1 0.1
in point3.s sph 1 1 2 0.1
r all_points.g u point1.s u point2.s u point3.s B all_points.g

Tuesday, June 25th, 2024[edit]

Add sample methods: 

RayParam SampleRandom(size_t num);
RayParam SampleSphere(size_t num);
RayParam UniformSphere(size_t num);

Wednesday, June 26th, 2024[edit]

Finish store res as json file,like this: { 

       "dir": [
           0.46341427145648684,
           -0.6747185194294957,
           -0.5744581207967407
       ],
       "point": [
           -30.10931324293444,
           72.95779116737057,
           81.61656328468132
       ],
       "rgb": [
           173,
           89,
           174
       ]
   }

}

Sunday, June 30th, 2024[edit]

Finish my first nerual rendering and genertae a picture.

Monday, July 1st, 2024[edit]

convert coordinate data to spherical data. create dataset and related methods.

Tuesday, July 2nd, 2024[edit]

There are some errors in coordinate convert, I fixed them all

Wednesday, July 3rd, 2024[edit]

Write a deep resnet to train, it doesn't work

Thursday, July 4th, 2024[edit]

Try to improve resnet performance by modifying hyperparameters

Friday, July 5th, 2024[edit]

Get a great result with resnet

Monday, July 8st, 2024[edit]

finish grid net with fixed dir, the result was not so bad

Tuesday, July 9nd, 2024[edit]

finish grid net with any dir, the result was too bad

Wednesday, July 10th, 2024[edit]

I use a 4-dimensional network which uses both dir and pos to train, it is very hard to train

Tuesday, July 11st, 2024[edit]

get some result with a 128*128*96*96*3 grid net, it doesn't work well.

Friday, July 12nd, 2024[edit]

Read some paper about Nerf. I mentioned this:NeRF: Representing Scenes as Neural Radiance Fields for View Synthesis, they used a A100 to train and it costs more than two days.

Monday, July 15st, 2024[edit]

I am thinking aboud rendering loss func. Actually I think the function is not differentiable, which is probably the main reason why the training is not good.

Tuesday, July 16-18st, 2024[edit]

I spent a lot of time reading papers on NERF: [VIINTER: View Interpolation with Implicit Neural Representations of Images](https://arxiv.org/pdf/2211.00722) [Direct Voxel Grid Optimization: Super-fast Convergence for Radiance Fields Reconstruction](https://arxiv.org/pdf/2111.11215) [NeRF++: Analyzing and improving neural radiance fields](https://arxiv.org/pdf/2010.07492) etc...

Mondey, July 22st, 2024[edit]

I decide to use 3d gaussian splatting to improve my network. I am reading this realization:https://github.com/graphdeco-inria/gaussian-splatting

Tuesdey, July 22st, 2024[edit]

reading Matteo's codes....

Retrieved from "https://brlcad.org/w/index.php?title=User:Jin_Ke&oldid=12774"