GitLab

* single build

* attemp fix aws listing

* fix

* fix

* fix

* fix

* fix

* fix

* fix

* fix

* fix format

* fix format

Co-authored-by: chihaoliang(chihaoliang) <chihaoliang@tencent.com>

* add test mode render_image_with_occgrid

* fix format

* misc fix

* add mark_invisible_cells in occ_grid

add test mode for traverse_grids

* add data type to mark_invisible_cells

* add test for mark_invisible_cells & test mode traverse_grids

* upd comments

* ndr trial

* merge traverse_grids with traverse_grids_test in C

* fix format

* Revert "fix format"

This reverts commit 6233fc4e3a4ea4643ace6a96d28ad32c6a3a444f.

* revert benchmarks changes

* remove MLP updates

* Revert "remove MLP updates"

This reverts commit c37d199463e1d1fd2d28e061137391fe1b01b537.

* revert benchmarks changes

* add assert in traverse_grids

* Revert "add assert in traverse_grids"

This reverts commit c93eaad20b7e53f8dca49a3f9af97b549b7092fc.

* revert benchmarks changes

* reduce mem for traverse grid with over_allocate=True

* cleanup doc

* final cleanup with mark_invisible_cells

* ndr trial

* fix occ grid invisible cell filtering

---------
Co-authored-by: Ruilong Li <ruilongli94@gmail.com>

* ndr trial

* remove unused cuda code

* remove unused python code

* remove unused python code

* scan.cu is able to deal with empty inputs

* fix when network input is empty

* fix when network input is empty

* fix when network input is empty

* revert benchmarks submodules

* remove unused mlp model

* add pre-computed transmittance_

* add prefix_trans to all render  functions

* Fixed traversal with far_plane

* test added for traversal with near and far planes

* More correct test

* black formatting for test

* Per-ray min-max distances in sampling

* Test for sampling with min/max distances added

* black formatting

* Fixed traversal with far_plane

* test added for traversal with near and far planes

* More correct test

* black formatting for test

* opencv_lens_undistortion

* fix k4 bug for undistortion, support fisheye

* support k3 k4 k5 k6

* fix _opencv_len_distortion; format

* naming: len->lens

* update workflow; fix Literal

* fix format

* fix typo

* fix workflow for cu102

* update workflow; fix Literal

* fix format

* fix typo

* update workflow; fix Literal

* fix format

* update workflow

* tiny fix

* format

* format

* fix workflow

* fix workflow

* update cuda env file

* update workflow

* tiny fix

* format

* format

* fix workflow

* fix workflow

* update workflow

* tiny fix

* format

* format

* fix workflow

* update workflow

* tiny fix

* format

* format

* missing docs for the 4 dropin examples

* fix docs

* profiling in coding.rst

update the doc

* importance_sampling with test

* package importance_sampling

* compute_intervals tested and packaged

* compute_intervals_v2

* bicycle is failing

* fix cut in compute_intervals_v2, test pass for rendering

* hacky way to get opaque_bkgd work

* reorg ING

* PackedRaySegmentsSpec

* chunk_ids -> ray_ids

* binary -> occupied

* test_traverse_grid_basic checked

* fix traverse_grid with step size, checked

* support max_step_size, not verified

* _cuda and cuda; upgrade ray_marching

* inclusive scan

* test_exclusive_sum but seems to have numeric error

* inclusive_sum_backward verified

* exclusive sum backward

* merge fwd and bwd for scan

* inclusive & exclusive prod verified

* support normal scan with torch funcs

* rendering and tests

* a bit clean up

* importance_sampling verified

* stratified for importance_sampling

* importance_sampling in pdf.py

* RaySegmentsSpec in data_specs; fix various bugs

* verified with _proposal_packed.py

* importance sampling support batch input/output. need to verify

* prop script with batch samples

* try to use cumsum  instead of cumprod

* searchsorted

* benchmarking prop

* ray_aabb_intersect untested

* update prop benchmark numbers

* minor fixes

* batched ray_aabb_intersect

* ray_aabb_intersect and traverse with grid(s)

* tiny optimize for traverse_grids kernels

* traverse_grids return intervals and samples

* cub not verified

* cleanup

* propnet and occgrid as estimators

* training print iters 10k

* prop is good now

* benchmark in google sheet.

* really cleanup: scan.py and test

* pack.py and test

* rendering and test

* data_specs.py and pdf.py docs

* data_specs.py and pdf.py docs

* init and headers

* grid.py and test for it

* occ grid docs

* generated docs

* example docs for pack and scan function.

* doc fix for volrend.py

* doc fix for pdf.py

* fix doc for rendering function

* docs

* propnet docs

* update scripts

* docs: index.rst

* methodology docs

* docs for examples

* mlp nerf script

* update t-nerf script

* rename dnerf to tnerf

* misc update

* bug fix: pdf_loss with test

* minor fix

* update readme with submodules

* fix format

* update gitingore file

* fix doc failure. teaser png to jpg

* docs in examples/

* Fix train_mlp_nerf

* Fix black and isort