- 03 Sep, 2022 1 commit
-
-
Pyre Bot Jr authored
Reviewed By: stroxler Differential Revision: D39230408 fbshipit-source-id: dce7a461507ee7199f588341773096c06051b2dc
-
- 02 Sep, 2022 1 commit
-
-
Jiali Duan authored
Summary: Update the docstring for try_get_projection_transform on the API design. Reviewed By: kjchalup Differential Revision: D39227333 fbshipit-source-id: c9d0e625735d4972116d1f71865fb9b763e684de
-
- 01 Sep, 2022 2 commits
-
-
Jiali Duan authored
Summary: Fixed the typing for try_get_projection_transform. Reviewed By: kjchalup Differential Revision: D39211811 fbshipit-source-id: ef05c6b545831d1a9f3c754aeb02fb9776e360ed
-
Pyre Bot Jr authored
Reviewed By: kjchalup Differential Revision: D39198333 fbshipit-source-id: 3f4ebcf625215f21d165073837578ff69b05f72d
-
- 31 Aug, 2022 6 commits
-
-
Jiali Duan authored
Summary: 1) Update rasterizer/point rasterizer to accommodate fisheyecamera. Specifically, transform_points is in placement of explicit transform compositions. 2) In rasterizer unittests, update corresponding tests for rasterizer and point_rasterizer. Address comments to test fisheye against perspective camera when distortions are turned off. 3) Address comments to add end2end test for fisheyecameras. In test_render_meshes, fisheyecameras are added to camera enuerations whenever possible. 4) Test renderings with fisheyecameras of different params on cow mesh. 5) Use compositions for linear cameras whenever possible. Reviewed By: kjchalup Differential Revision: D38932736 fbshipit-source-id: 5b7074fc001f2390f4cf43c7267a8b37fd987547
-
Jiali Duan authored
Summary: Amend FisheyeCamera by adding tests for all combination of params and for different batch_sizes. Reviewed By: kjchalup Differential Revision: D39176747 fbshipit-source-id: 830d30da24beeb2f0df52db0b17a4303ed53b59c
-
Chris Lambert authored
Summary: Remove the compat functions eigh, solve, lstsq, and qr. Migrate callers to use torch.linalg directly. Reviewed By: bottler Differential Revision: D39172949 fbshipit-source-id: 484230a553237808f06ee5cdfde64651cba91c4c
-
Jeremy Reizenstein authored
Summary: A dummy value in test_opengl_utils seems to be able to break tests in test_mesh_renderer_opengl{,_to}. Reviewed By: kjchalup Differential Revision: D39173275 fbshipit-source-id: 83b15159f70135ea575d5085c7b6b37badd6e49e -
Krzysztof Chalupka authored
Summary: D38919607 (https://github.com/facebookresearch/pytorch3d/commit/c4545a7cbc7bea5fce9862ae45fcff171e9204f9) and D38858887 (https://github.com/facebookresearch/pytorch3d/commit/06cbba2628265a7c8a69eec732b4f0145b6a204b) were premature, turns out CUDA 10.2 doesn't support C++17. Reviewed By: bottler Differential Revision: D39156205 fbshipit-source-id: 5e2e84cc4a57d1113a915166631651d438540d56
-
Sergii Dymchenko authored
Summary: torch.symeig is deprecated for a long time and is being removed by https://github.com/pytorch/pytorch/pull/70988. Created from CodeHub with https://fburl.com/edit-in-codehub Reviewed By: bottler Differential Revision: D39153103 fbshipit-source-id: 3a1397b6d86fb3e45e4777e06a4da3ee76591b32
-
- 30 Aug, 2022 1 commit
-
-
David Novotny authored
Summary: Adds yaml configs to train selected methods on CO3Dv2. Few more updates: 1) moved some fields to base classes so that we can check is_multisequence in experiment.py 2) skip loading all train cameras for multisequence datasets, without this, co3d-fewview is untrainable 3) fix bug in json index dataset provider v2 Reviewed By: kjchalup Differential Revision: D38952755 fbshipit-source-id: 3edac6fc8e20775aa70400bd73a0e6d52b091e0c
-
- 28 Aug, 2022 2 commits
-
-
Jiali Duan authored
Summary: Address comments to add benchmarkings for cameras and the new fisheye cameras. The dependency functions in test_cameras have been updated in Diff 1. The following two snapshots show benchmarking results. Reviewed By: kjchalup Differential Revision: D38991914 fbshipit-source-id: 51fe9bb7237543e4ee112c9f5068a4cf12a9d482
-
Jiali Duan authored
Summary: 1. A Fisheye camera model that generalizes pinhole camera by considering distortions (i.e. radial, tangential and thin-prism distortions). 2. Added tests against perspective cameras when distortions are off and Aria data points when distortions are on. 3. Address comments to test unhandled shapes between points and transforms. Added tests for __FIELDS, shape broadcasts, cuda etc. 4. Address earlier comments for code efficiency (e.g., adopted torch.norm; torch.solve for matrix inverse; removed inplace operations; unnecessary clone; expand in place of repeat etc). Reviewed By: jcjohnson Differential Revision: D38407094 fbshipit-source-id: a3ab48c85c496ac87af692d5d461bb3fc2a2db13
-
- 26 Aug, 2022 2 commits
-
-
Darijan Gudelj authored
Summary: I think there is a typo here could not find any MultiPassEARenderer just MultiPassEmissionAbsorptionRenderer? Reviewed By: bottler Differential Revision: D39056641 fbshipit-source-id: 4dd0b123fc795a0083a957786c032e23dc5abac9
-
Darijan Gudelj authored
Summary: Added replacable decoding functions which will be applied after the voxel grid to get color and density Reviewed By: bottler Differential Revision: D38829763 fbshipit-source-id: f21ce206c1c19548206ea2ce97d7ebea3de30a23
-
- 25 Aug, 2022 1 commit
-
-
Darijan Gudelj authored
Summary: Simple wrapper around voxel grids to make them a module Reviewed By: bottler Differential Revision: D38829762 fbshipit-source-id: dfee85088fa3c65e396cc7d3bf7ebaaffaadb646
-
- 23 Aug, 2022 7 commits
-
-
Krzysztof Chalupka authored
Summary: One of the docstrings is a disaster see https://pytorch3d.readthedocs.io/en/latest/modules/ops.html Also some minor fixes I encountered when browsing the code Reviewed By: bottler Differential Revision: D38581595 fbshipit-source-id: 3b6ca97788af380a44df9144a6a4cac782c6eab8
-
Krzysztof Chalupka authored
Add structured bindings to iou to prove that we're C++17-friendly. Also other minor improvements to bbox iou Summary: Recently we removed C++14-only compilation, should work. Reviewed By: bottler Differential Revision: D38919607 fbshipit-source-id: 6a26fa7713f7ba2163364ccc673ad774aa3a5adb
-
Jeremy Reizenstein authored
Summary: Fix issue #1306 Reviewed By: kjchalup Differential Revision: D38941342 fbshipit-source-id: 306ea698ab6af22b874df6e2abdaa9021b65e1ef
-
Krzysztof Chalupka authored
Summary: https://github.com/facebookresearch/pytorch3d/issues/736 Reviewed By: bottler Differential Revision: D38881935 fbshipit-source-id: 62aa3575513ab752a5afda4a257a985032bc7f6d
-
Darijan Gudelj authored
Summary: Moved the MLP and transformer from nerf to a new file to be reused. Reviewed By: bottler Differential Revision: D38828150 fbshipit-source-id: 8ff77b18b3aeeda398d90758a7bcb2482edce66f
-
Darijan Gudelj authored
Summary: Added voxel grid classes from TensoRF, both in their factorized (CP and VM) and full form. Reviewed By: bottler Differential Revision: D38465419 fbshipit-source-id: 8b306338af58dc50ef47a682616022a0512c0047
-
Jeremy Reizenstein authored
Summary: Stop stale workflow Reviewed By: kjchalup Differential Revision: D38858730 fbshipit-source-id: 25a5c00a0295739bac841ca6f0d5ff8230e689d0
-
- 22 Aug, 2022 1 commit
-
-
Georgia Gkioxari authored
Summary: Fix EPS issue that causes numerical instabilities when boxes are very close Reviewed By: kjchalup Differential Revision: D38661465 fbshipit-source-id: d2b6753cba9dc2f0072ace5289c9aa815a1a29f6
-
- 21 Aug, 2022 2 commits
-
-
Jeremy Reizenstein authored
Summary: Remove compiler arguments which insist on C++14. Reviewed By: kjchalup Differential Revision: D38858887 fbshipit-source-id: 542173ec97cacfa724d14c8a4b9ce9dc2457c5d5
-
Jeremy Reizenstein authored
Summary: Fix outdated info Reviewed By: kjchalup Differential Revision: D38858766 fbshipit-source-id: 52b120f355e8f9e86d777875627af02c80ee45b6
-
- 19 Aug, 2022 2 commits
-
-
Max Wasylow authored
Summary: Removing hardcoded block reduction operation from `sample_farthest_points.cu` code, and replace it with `cub::BlockReduce` reducing complexity of the code, and letting established libraries do the thinking for us. Reviewed By: bottler Differential Revision: D38617147 fbshipit-source-id: b230029c55f05cda0aab1648d3105a8d3e92d27b
-
David Novotny authored
Summary: Fixes the blender synthetic configs. Reviewed By: kjchalup Differential Revision: D38786095 fbshipit-source-id: 6d0784ced41a3f2904f074221108cdb56bd20e7f
-
- 18 Aug, 2022 3 commits
-
-
Darijan Gudelj authored
Summary: Split Volumes class to data and location part so that location part can be reused in planned VoxelGrid classes. Reviewed By: bottler Differential Revision: D38782015 fbshipit-source-id: 489da09c5c236f3b81961ce9b09edbd97afaa7c8
-
Jeremy Reizenstein authored
Summary: generic_model_args no longer exists. Update some references to it, mostly in doc. This fixes the testing of all the yaml files in test_forward pass. Reviewed By: shapovalov Differential Revision: D38789202 fbshipit-source-id: f11417efe772d7f86368b3598aa66c52b1309dbf
-
Jeremy Reizenstein authored
Reviewed By: shapovalov Differential Revision: D38794764 fbshipit-source-id: 140c8a935d760bab8569d903cc52ac3dd73cd553
-
- 17 Aug, 2022 2 commits
-
-
Christoph Lassner authored
Summary: We identified that these logging statements can deteriorate performance in certain cases. I propose removing them from the regular renderer implementation and letting individuals re-insert debug logging wherever needed on a case-by-case basis. Pull Request resolved: https://github.com/facebookresearch/pytorch3d/pull/1260 Reviewed By: kjchalup Differential Revision: D38737439 Pulled By: bottler fbshipit-source-id: cf9dcbbeae4dbf214c2e17d5bafa00b2ff796393
-
Roman Shapovalov authored
Summary: Useful for visualising colmap output where some frames are not correctly registered. Reviewed By: bottler Differential Revision: D38743191 fbshipit-source-id: e823df2997870dc41d76784e112d4349f904d311
-
- 16 Aug, 2022 2 commits
-
-
Roman Shapovalov authored
Summary: Reasonable to expect bool indexing. Reviewed By: bottler, kjchalup Differential Revision: D38741446 fbshipit-source-id: 22b607bf13110043c5624196c66ca1484fdbce6c
-
Ashish Sinha authored
Summary: fixes typo of the docstring. Pull Request resolved: https://github.com/facebookresearch/pytorch3d/pull/1293 Differential Revision: D38737416 Pulled By: bottler fbshipit-source-id: 3f9da3e97b55c2acd858263de9e85eaee272a98f
-
- 15 Aug, 2022 3 commits
-
-
David Novotny authored
Summary: Previously, "psnr" was evaluated between the masked g.t. image and the render. To avoid confusion, "psnr" is now renamed to "psnr_masked". Reviewed By: bottler Differential Revision: D38707511 fbshipit-source-id: 8ee881ab1a05453d6692dde9782333a47d8c1234
-
Jeremy Reizenstein authored
Summary: Builds for new PyTorch 1.12.1. Drop builds for PyTorch 1.8.0 and 1.8.1. Reviewed By: kjchalup Differential Revision: D38658991 fbshipit-source-id: 6192e226c2154cd051eeee98498d9a395cfd6fd5
-
David Novotny authored
Summary: Adds additional source views to the eval batches for evaluating many-view models on CO3D Challenge Reviewed By: bottler Differential Revision: D38705904 fbshipit-source-id: cf7d00dc7db926fbd1656dd97a729674e9ff5adb
-
- 13 Aug, 2022 1 commit
-
-
Jeremy Reizenstein authored
Summary: 0.6.2 and 0.7.0 Reviewed By: kjchalup Differential Revision: D38659393 fbshipit-source-id: eb99f3fbe381039b391419c878b7bbac4a88d619
-
- 12 Aug, 2022 1 commit
-
-
David Novotny authored
Summary: Reports also the PSNR between the unmasked G.T. image and the render. Reviewed By: bottler Differential Revision: D38655943 fbshipit-source-id: 1603a2d02116ea1ce037e5530abe1afc65a2ba93
-