MMDetection3D V0.17.1 Release

Highlights

• Support a faster but non-deterministic version of hard voxelization
• Completion of dataset tutorials and the Chinese documentation
• Improved the aesthetics of the documentation format

Improvements

• Add Chinese Documentation for training on customized datasets and designing customized models (#729, #820)
• Support a faster but non-deterministic version of hard voxelization (#904)
• Update paper titles and code details for metafiles (#917)
• Add a tutorial for KITTI dataset (#953)
• Use Pytorch sphinx theme to improve the format of documentation (#958)
• Use the docker to accelerate CI (#971)

Bug Fixes

• Fix the sphinx version used in the documentation (#902)
• Fix a dynamic scatter bug that discards the first voxel by mistake when all input points are valid (#915)
• Fix the inconsistent variable names used in the unit test for voxel generator (#919)
• Upgrade to use build_prior_generator to replace the legacy build_anchor_generator (#941)
• Fix a minor bug caused by a too-small difference set in the FreeAnchor Head (#944)

Contributors

A total of 8 developers contributed to this release.

@DCNSW, @zhanggefan, @mickeyouyou, @ZCMax, @wHao-Wu, @tojimahammatov, @xiliu8006, @Tai-Wang

New Contributors

• @mickeyouyou made their first contribution in #920
• @tojimahammatov made their first contribution in #944

Full Changelog: v0.17.0...v0.17.1

MMDetection3D V0.17.0 Release

Compatibility

• Unify the camera keys for consistent transformation between coordinate systems on different datasets. The modification changes the key names to lidar2img, depth2img, cam2img, etc. for easier understanding. Customized codes using legacy keys may be influenced.
• The next release will begin to move files of CUDA ops to MMCV. It will influence the way to import related functions. We will not break the compatibility but will raise a warning first and please prepare to migrate it.

Highlights

• Support 3D object detection on the S3DIS dataset
• Support compilation on Windows
• Full benchmark for PAConv on S3DIS
• Further enhancement for documentation, especially on the Chinese documentation

New Features

• Support 3D object detection on the S3DIS dataset (#835)

Improvements

• Support point sampling based on distance metric (#667, #840)
• Update PointFusion to support unified camera keys (#791)
• Add Chinese documentation for customized dataset (#792), data pipeline (#827), customized runtime (#829), 3D Detection on ScanNet (#836), nuScenes (#854) and Waymo (#859)
• Unify camera keys used in the transformation between different systems (#805)
• Add a script to support benchmark regression (#808)
• Benchmark PAConvCUDA on S3DIS (#847)
• Add a tutorial for 3D detection on the Lyft dataset (#849)
• Support to download pdf and epub documentation (#850)
• Change the repeat setting in Group-Free-3D configs to reduce training epochs (#855)

Bug Fixes

• Fix compiling errors on Windows (#766)
• Fix the deprecated NMS setting in the ImVoteNet config (#828)
• Use the latest wrap_fp16_model import from MMCV (#861)
• Remove 2D annotations generation on Lyft (#867)
• Update index files for the Chinese documentation to be consistent with the English version (#873)
• Fix the nested list transpose in the CenterPoint head (#879)
• Fix deprecated pretrained model loading for RegNet (#889)

Contributors

A total of 11 developers contributed to this release.

@THU17cyz, @wHao-Wu, @wangruohui, @Wuziyi616, @filaPro, @ZwwWayne, @Tai-Wang, @DCNSW, @xieenze, @robin-karlsson0, @ZCMax

New Contributors

• @wangruohui made their first contribution in #766
• @xieenze made their first contribution in #872
• @robin-karlsson0 made their first contribution in #879

Full Changelog: v0.16.0...v0.17.0

MMDetection3D V0.16.0 Release

Compatibility

• Remove the rotation and dimension hack in the monocular 3D detection on nuScenes by applying corresponding transformation in the pre-processing and post-processing. The modification only influences nuScenes coco-style json files. Please re-run the data preparation scripts if necessary. See more details in the PR #744.
• Add a new pre-processing module for the ScanNet dataset in order to support multi-view detectors. Please run the updated scripts to extract the RGB data and its annotations. See more details in the PR #696.

Highlights

• Support to use MIM with pip installation
• Support PAConv models and benchmarks on S3DIS
• Enhance the documentation especially on dataset tutorials

New Features

• Support RGB images on ScanNet for multi-view detectors (#696)
• Support FLOPs and number of parameters calculation (#736)
• Support to use MIM with pip installation (#782)
• Support PAConv models and benchmarks on the S3DIS dataset (#783, #809)

Improvements

• Refactor Group-Free-3D to make it inherit BaseModule from MMCV (#704)
• Modify the initialization methods of FCOS3D to be consistent with the refactored approach (#705)
• Benchmark the Group-Free-3D models on ScanNet (#710)
• Add Chinese Documentation for Getting Started (#725), FAQ (#730), Model Zoo (#735), Demo (#745), Quick Run (#746), Data Preparation (#787) and Configs (#788)
• Add documentation for semantic segmentation on ScanNet and S3DIS (#743, #747, #806, #807)
• Add a parameter max_keep_ckpts to limit the maximum number of saved Group-Free-3D checkpoints (#765)
• Add documentation for 3D detection on SUN RGB-D and nuScenes (#770, #793)
• Remove mmpycocotools in the Dockerfile (#785)

Bug Fixes

• Fix versions of OpenMMLab dependencies (#708)
• Convert rt_mat to torch.Tensor in coordinate transformation for compatibility (#709)
• Fix the bev_range initialization in ObjectRangeFilter according to the gt_bboxes_3d type (#717)
• Fix Chinese documentation and incorrect doc format due to the incompatible Sphinx version (#718)
• Fix a potential bug when setting interval == 1 in analyze_logs.py (#720)
• Update the structure of Chinese Documentation (#722)
• Fix FCOS3D FPN BC-Breaking caused by the code refactoring in MMDetection (#739)
• Fix wrong in_channels when with_distance=True in the Dynamic VFE Layers (#749)
• Fix the dimension and yaw hack of FCOS3D on nuScenes (#744, #794, #795, #818)
• Fix the missing default bbox_mode in the show_multi_modality_result (#825)

Contributors

A total of 12 developers contributed to this release.

@yinchimaoliang, @gopi231091, @filaPro, @ZwwWayne, @ZCMax, @hjin2902, @wHao-Wu, @Wuziyi616, @xiliu8006, @THU17cyz, @DCNSW, @Tai-Wang

New Contributors

• @gopi231091 made their first contribution in #709

Full Changelog: v0.15.0...v0.16.0

MMDetection3D V0.15.0 Release

Highlights

• Support PAConv
• Support monocular/multi-view 3D detector ImVoxelNet on KITTI
• Support Transformer-based 3D detection method Group-Free-3D on ScanNet
• Add documentation for tasks including LiDAR-based 3D detection, vision-only 3D detection and point-based 3D semantic segmentation
• Add dataset documents like ScanNet
• Upgrade to use MMCV-full v1.3.8

Compatibility

In order to fix the problem that the priority of EvalHook is too low, all hook priorities have been re-adjusted in 1.3.8, so MMDetection 2.14.0 needs to rely on the latest MMCV 1.3.8 version. For related information, please refer to #1120, for related issues, please refer to #5343.

New Features

• Support Group-Free-3D on ScanNet (#539)
• Support PAConv modules (#598, #599)
• Support ImVoxelNet on KITTI (#627, #654)

Improvements

• Add unit tests for pipeline functions LoadImageFromFileMono3D, ObjectNameFilter and ObjectRangeFilter (#615)
• Enhance IndoorPatchPointSample (#617)
• Refactor model initialization methods based MMCV (#622)
• Add Chinese docs (#629)
• Add documentation for LiDAR-based 3D detection (#642)
• Unify intrinsic and extrinsic matrices for all datasets (#653)
• Add documentation for point-based 3D semantic segmentation (#663)
• Add documentation of ScanNet for 3D detection (#664)
• Refine docs for tutorials (#666)
• Add documentation for vision-only 3D detection (#669)
• Refine docs for Quick Run and Useful Tools (#686)

Bug Fixes

• Fix the bug of BackgroundPointsFilter using the bottom center of ground truth (#609)
• Fix LoadMultiViewImageFromFiles to unravel stacked multi-view images to list to be consistent with DefaultFormatBundle (#611)
• Fix the potential bug in analyze_logs when the training resumes from a checkpoint or is stopped before evaluation (#634)
• Fix test commands in docs and make some refinements (#635)
• Fix wrong config paths in unit tests (#641)

Full Changelog: v0.14.0...v0.15.0

MMDetection3D V0.14.0 Release

Highlights

• Support the point cloud segmentation method PointNet++

New Features

• Support PointNet++ (#479, #528, #532, #541)
• Support RandomJitterPoints transform for point cloud segmentation (#584)
• Support RandomDropPointsColor transform for point cloud segmentation (#585)

Improvements

• Move the point alignment of ScanNet from data pre-processing to pipeline (#439, #470)
• Add compatibility document to provide detailed descriptions of BC-breaking changes (#504)
• Add MMSegmentation installation requirement (#535)
• Support points rotation even without bounding box in GlobalRotScaleTrans for point cloud segmentaiton (#540)
• Support visualization of detection results and dataset browse for nuScenes Mono-3D dataset (#542, #582)
• Support faster implementation of KNN (#586)
• Support RegNetX models on Lyft dataset (#589)
• Remove a useless parameter label_weight from segmentation datasets including Custom3DSegDataset, ScanNetSegDataset and S3DISSegDataset (#607)

Bug Fixes

• Fix a corrupted lidar data file in Lyft dataset in data_preparation (#546)
• Fix evaluation bugs in nuScenes and Lyft dataset (#549)
• Fix converting points between coordinates with specific transformation matrix in the coord_3d_mode.py (#556)
• Support PointPillars models on Lyft dataset (#578)
• Fix the bug of demo with pre-trained VoteNet model on ScanNet (#600)

New Contributors

• @haotian-liu made their first contribution in #515
• @JSchuurmans made their first contribution in #565

Full Changelog: v0.13.0...v0.14.0

MMDetection3D V0.13.0 Release

Highlights

• Support a monocular 3D detection method FCOS3D
• Support ScanNet and S3DIS semantic segmentation dataset
• Enhancement of visualization tools for dataset browsing and demos, including support of visualization for multi-modality data and point cloud segmentation.

New Features

• Support ScanNet semantic segmentation dataset (#390)
• Support monocular 3D detection on nuScenes (#392)
• Support multi-modality visualization (#405)
• Support nuImages visualization (#408)
• Support monocular 3D detection on KITTI (#415)
• Support online visualization of semantic segmentation results (#416)
• Support ScanNet test results submission to online benchmark (#418)
• Support S3DIS data pre-processing and dataset class (#433)
• Support FCOS3D (#436, #442, #482, #484)
• Support dataset browse for multiple types of datasets (#467)
• Adding paper-with-code (PWC) metafile for each model in the model zoo (#485)

Improvements

• Support dataset browsing for SUNRGBD, ScanNet or KITTI points and detection results (#367)
• Add the pipeline to load data using file client (#430)
• Support to customize the type of runner (#437)
• Make pipeline functions process points and masks simultaneously when sampling points (#444)
• Add waymo unit tests (#455)
• Split the visualization of projecting points onto image from that for only points (#480)
• Efficient implementation of PointSegClassMapping (#489)
• Use the new model registry from mmcv (#495)

Bug Fixes

• Fix Pytorch 1.8 Compilation issue in the scatter_points_cuda.cu (#404)
• Fix dynamic_scatter errors triggered by empty point input (#417)
• Fix the bug of missing points caused by using break incorrectly in the voxelization (#423)
• Fix the missing coord_type in the waymo dataset config (#441)
• Fix errors in four unittest functions of configs, test_detectors.py, test_heads.py (#453)
• Fix 3DSSD training errors and simplify configs (#462)
• Clamp 3D votes projections to image boundaries in ImVoteNet (#463)
• Update out-of-date names of pipelines in the config of pointpillars benchmark (#474)
• Fix the lack of a placeholder when unpacking RPN targets in the h3d_bbox_head.py (#508)
• Fix the incorrect value of K when creating pickle files for SUN RGB-D (#511)

New Contributors

• @gillbam made their first contribution in #423
• @Divadi made their first contribution in #463
• @virusapex made their first contribution in #511

Full Changelog: v0.12.0...v0.13.0

MMDetection3D V0.12.0 Release

Highlights

• Support a new multi-modality method ImVoteNet.
• Support pytorch 1.7 and 1.8
• Refactor the structure of tools and train.py/test.py

Bug Fixes

• Fix missing keys coord_type in database sampler config (#345)
• Rename H3DNet configs (#349)
• Fix CI by using ubuntu 18.04 in github workflow (#350)
• Add assertions to avoid 4-dim points being input to points_in_boxes (#357)
• Fix the SECOND results on Waymo in the corresponding README (#363)
• Fix the incorrectly adopted pipeline when adding val to workflow (#370)
• Fix a potential bug when indices used in the backwarding in ThreeNN (#377)
• Fix a compilation error triggered by scatter_points_cuda.cu in pytorch 1.7 (#393)

New Features

• Support LiDAR-based semantic segmentation metrics (#332)
• Support ImVoteNet (#352, #384)
• Support the KNN GPU operation (#360, #371)

Improvements

• Add FAQ for common problems in the documentation (#333)
• Refactor the structure of tools (#339)
• Refactor train.py and test.py (#343)
• Support demo on nuScenes (#353)
• Add 3DSSD checkpoints (#359)
• Update the Bibtex of CenterPoint (#368)
• Add citation format and reference to other OpenMMLab projects in the README (#374)
• Upgrade the mmcv version requirements (#376)
• Add numba and numpy version requirements in FAQ (#379)
• Avoid unnecessary for-loop execution of VFE layer creation (#389)
• Update SUNRGBD dataset documentation to stress the requirements for training ImVoteNet (#391)
• Modify vote head to support 3DSSD (#396)

New Contributors

• @tianweiy made their first contribution in #368
• @happynear made their first contribution in #363
• @zehuichen123 made their first contribution in #389

Full Changelog: v0.11.0...v0.12.0

MMDetection3D V0.11.0 Release

Highlights

• Support more friendly visualization interfaces based on open3d
• Support a faster and more memory-efficient implementation of DynamicScatter
• Refactor unit tests and details of configs

Bug Fixes

• Fix an unsupported bias setting in the unit test for CenterPoint head (#304)
• Fix errors due to typos in the CenterPoint head (#308)
• Fix a minor bug in points_in_boxes.py when tensors are not in the same device. (#317)

New Features

• Support new visualization methods based on Open3D (#284, #323)

Improvements

• Refactor unit tests (#303)
• Move the key train_cfg and test_cfg into the model configs (#307)
• Update README with Chinese version and instructions for getting started. (#310, #316)
• Support a faster and more memory-efficient implementation of DynamicScatter (#318, #326)
• Fix warning of deprecated usages of nonzero during training with PyTorch 1.6 (#330)

Full Changelog: v0.10.0...v0.11.0

MMDetection3D V0.10.0 Release

Highlights

• Preliminary release of API for SemanticKITTI dataset.
• Documentation and demo enhancement for better user experience.
• Fix a number of underlying minor bugs and add some corresponding important unit tests.

Bug Fixes

• Fixed the issue of unpacking size in furthest_point_sample.py (#248)
• Fix bugs for 3DSSD triggered by empty ground truths (#258)
• Remove models without checkpoints in model zoo statistics of documentation (#259)
• Fix some unclear installation instructions in getting_started.md (#269)
• Fix relative paths/links in the documentation (#271)
• Fix a minor bug in scatter_points_cuda.cu when num_features != 4 (#275)
• Fix the bug about missing text files when testing on KITTI (#278)
• Fix issues caused by inplace modification of tensors in BaseInstance3DBoxes (#283)
• Fix log analysis for evaluation and adjust the documentation accordingly (#285)

New Features

• Support SemanticKITTI dataset preliminarily (#287)

Improvements

• Add tags to README in configurations for specifying different uses (#262)
• Update instructions for evaluation metrics in the documentation (#265)
• Add nuImages entry in README.md and gif demo (#266, #268)
• Add unit test for voxelization (#275)

New Contributors

• @congee524 made their first contribution in #259
• @wikiwen made their first contribution in #269
• @EricWiener made their first contribution in #248

Full Changelog: v0.9.0...v0.10.0

MMDetection3D V0.9.0 Release

Highlights

• Documentation refactoring with better structure, especially about how to implement new models and customized datasets.
• More compatible with refactored point structure by bug fixes in ground truth sampling.

Bug Fixes

• Fix point structure related bugs in ground truth sampling (#211)
• Fix loading points in ground truth sampling augmentation on nuScenes (#221)
• Fix channel setting in the SeparateHead of CenterPoint (#228)
• Fix evaluation for indoors 3D detection in case of less classes in prediction (#231)
• Remove unreachable lines in nuScenes data converter (#235)
• Minor adjustments of numpy implementation for perspective projection and prediction filtering criterion in KITTI evaluation (#241)

Improvements

• Documentation refactoring (#242)

New Contributors

• @meng-zha made their first contribution in #211
• @zhezhao1989 made their first contribution in #228

Full Changelog: v0.8.0...v0.9.0