{"url":"/dataset/camvid","name":"CamVid","full_name":"Cambridge-driving Labeled Video Database","description_markdown":"**CamVid** (**Cambridge-driving Labeled Video Database**) is a road/driving scene understanding database which was originally captured as five video sequences with a 960×720 resolution camera mounted on the dashboard of a car. Those sequences were sampled (four of them at 1 fps and one at 15 fps) adding up to 701 frames. Those stills were manually annotated with 32 classes: void, building, wall, tree, vegetation, fence, sidewalk, parking block, column/pole, traffic cone, bridge, sign, miscellaneous text, traffic light, sky, tunnel, archway, road, road shoulder, lane markings (driving), lane markings (non-driving), animal, pedestrian, child, cart luggage, bicyclist, motorcycle, car, SUV/pickup/truck, truck/bus, train, and other moving object\r\n\r\nSource: [A Review on Deep Learning TechniquesApplied to Semantic Segmentation](https://arxiv.org/abs/1704.06857)\r\nImage Source: [http://mi.eng.cam.ac.uk/research/projects/VideoRec/CamVid/](http://mi.eng.cam.ac.uk/research/projects/VideoRec/CamVid/)","description_withheld":null,"homepage":"http://mi.eng.cam.ac.uk/research/projects/VideoRec/CamVid/","introduced_date":"2009-01-01","introduced_date_note":null,"introduced_by":{"paper":null,"title":"Semantic object classes in video: A high-definition ground truth database","first_author":null,"url":"https://doi.org/10.1016/j.patrec.2008.04.005"},"license":{"name":"Unknown","url":null},"modalities":[{"name":"Images","url":"/datasets/modality/images"},{"name":"Videos","url":"/datasets/modality/videos"}],"tasks":[{"name":"Semantic Segmentation","url":"/task/semantic-segmentation","datasets_with_task":"/datasets/task/semantic-segmentation"},{"name":"2D Semantic Segmentation","url":"/task/2d-semantic-segmentation","datasets_with_task":"/datasets/task/2d-semantic-segmentation"},{"name":"Real-Time Semantic Segmentation","url":"/task/real-time-semantic-segmentation","datasets_with_task":"/datasets/task/real-time-semantic-segmentation"},{"name":"Video Semantic Segmentation","url":"/task/video-semantic-segmentation","datasets_with_task":"/datasets/task/video-semantic-segmentation"}],"languages":[],"variants":["CamVid"],"data_loaders":[{"repo":"https://github.com/ENSTA-U2IS-AI/torch-uncertainty","url":"https://torch-uncertainty.github.io/","frameworks":["pytorch"]},{"repo":"https://github.com/zxchasing/CamVid","url":"https://github.com/zxchasing/CamVid","frameworks":["pytorch"]}],"num_papers_in_archive":227,"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28"},"benchmarks":[{"leaderboard":"/sota/real-time-semantic-segmentation-on-camvid","task":"Real-Time Semantic Segmentation","dataset_variant":"CamVid","rows":29,"metrics":["mIoU","Frame (fps)","Time (ms)"],"first_row_in_archive_order":{"model":"PIDNet-M (Cityscapes-Pretrained)","paper":"/paper/pidnet-a-real-time-semantic-segmentation","metrics":{"Frame (fps)":"85.6(3090)","Time (ms)":"11.7","mIoU":"82.0"},"code_links":[{"title":"XuJiacong/PIDNet","url":"https://github.com/XuJiacong/PIDNet"},{"title":"Darth-Kronos/PIDNet_TensorRT","url":"https://github.com/Darth-Kronos/PIDNet_TensorRT"},{"title":"hamidriasat/PIDNet","url":"https://github.com/hamidriasat/PIDNet"},{"title":"HengWeiBin/Oil-Polution-Dataset-with-PIDNet","url":"https://github.com/HengWeiBin/Oil-Polution-Dataset-with-PIDNet"},{"title":"Mahmood-Hussain/PIDNetTensorflow","url":"https://github.com/Mahmood-Hussain/PIDNetTensorflow"},{"title":"enot-autodl/lpcv-2023","url":"https://github.com/enot-autodl/lpcv-2023"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/semantic-segmentation-on-camvid","task":"Semantic Segmentation","dataset_variant":"CamVid","rows":21,"metrics":["Mean IoU","Global Accuracy"],"first_row_in_archive_order":{"model":"SERNet-Former","paper":"/paper/sernet-former-semantic-segmentation-by","metrics":{"Mean IoU":"84.62"},"code_links":[{"title":"serdarch/sernet-former","url":"https://github.com/serdarch/sernet-former"},{"title":"serdarch/SERNet-Former","url":"https://github.com/serdarch/SERNet-Former/blob/main/README.md"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/video-semantic-segmentation-on-camvid","task":"Video Semantic Segmentation","dataset_variant":"CamVid","rows":6,"metrics":["Mean IoU"],"first_row_in_archive_order":{"model":"TMANet-50","paper":"/paper/temporal-memory-attention-for-video-semantic","metrics":{"Mean IoU":"76.5"},"code_links":[{"title":"wanghao9610/TMANet","url":"https://github.com/wanghao9610/TMANet"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/2d-semantic-segmentation-on-camvid","task":"2D Semantic Segmentation","dataset_variant":"CamVid","rows":1,"metrics":["mIoU"],"first_row_in_archive_order":{"model":"SERNet-Former","paper":"/paper/sernet-former-semantic-segmentation-by","metrics":{"mIoU":"84.62"},"code_links":[{"title":"serdarch/sernet-former","url":"https://github.com/serdarch/sernet-former"},{"title":"serdarch/SERNet-Former","url":"https://github.com/serdarch/SERNet-Former/blob/main/README.md"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"}],"papers_with_a_benchmark_row":[{"paper":"/paper/dsnet-a-novel-way-to-use-atrous-convolutions","title":"DSNet: A Novel Way to Use Atrous Convolutions in Semantic Segmentation","date":"2024-06-06","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/sernet-former-semantic-segmentation-by","title":"SERNet-Former: Semantic Segmentation by Efficient Residual Network with Attention-Boosting Gates and Attention-Fusion Networks","date":"2024-01-28","rows_on_this_dataset":2,"code_links":2,"syntology":null},{"paper":"/paper/mobile-seed-joint-semantic-segmentation-and","title":"Mobile-Seed: Joint Semantic Segmentation and Boundary Detection for Mobile Robots","date":"2023-11-21","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/p2at-pyramid-pooling-axial-transformer-for","title":"P2AT: Pyramid Pooling Axial Transformer for Real-time Semantic Segmentation","date":"2023-10-23","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/rtformer-efficient-design-for-real-time","title":"RTFormer: Efficient Design for Real-Time Semantic Segmentation with Transformer","date":"2022-10-13","rows_on_this_dataset":2,"code_links":1,"syntology":null},{"paper":"/paper/s-textsuperscript-2-fpn-scale-ware-strip","title":"S$^2$-FPN: Scale-ware Strip Attention Guided Feature Pyramid Network for Real-time Semantic Segmentation","date":"2022-06-15","rows_on_this_dataset":3,"code_links":1,"syntology":null},{"paper":"/paper/pidnet-a-real-time-semantic-segmentation","title":"PIDNet: A Real-time Semantic Segmentation Network Inspired by PID Controllers","date":"2022-06-04","rows_on_this_dataset":3,"code_links":6,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":19,"samples_ran":1,"samples_unverified":18,"pointer_only_for_licence":1,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/pp-liteseg-a-superior-real-time-semantic","title":"PP-LiteSeg: A Superior Real-Time Semantic Segmentation Model","date":"2022-04-06","rows_on_this_dataset":2,"code_links":3,"syntology":null},{"paper":"/paper/the-devil-is-in-the-labels-semantic","title":"Scaling up Multi-domain Semantic Segmentation with Sentence Embeddings","date":"2022-02-04","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/rethink-dilated-convolution-for-real-time","title":"Rethinking Dilated Convolution for Real-time Semantic Segmentation","date":"2021-11-18","rows_on_this_dataset":1,"code_links":3,"syntology":null},{"paper":"/paper/temporal-memory-attention-for-video-semantic","title":"Temporal Memory Attention for Video Semantic Segmentation","date":"2021-02-17","rows_on_this_dataset":2,"code_links":1,"syntology":null},{"paper":"/paper/deep-dual-resolution-networks-for-real-time","title":"Deep Dual-resolution Networks for Real-time and Accurate Semantic Segmentation of Road Scenes","date":"2021-01-15","rows_on_this_dataset":3,"code_links":8,"syntology":null},{"paper":"/paper/hyperseg-patch-wise-hypernetwork-for-real","title":"HyperSeg: Patch-wise Hypernetwork for Real-time Semantic Segmentation","date":"2020-12-21","rows_on_this_dataset":2,"code_links":1,"syntology":null},{"paper":"/paper/bisenet-v2-bilateral-network-with-guided","title":"BiSeNet V2: Bilateral Network with Guided Aggregation for Real-time Semantic Segmentation","date":"2020-04-05","rows_on_this_dataset":4,"code_links":7,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":10,"samples_ran":6,"samples_unverified":4,"pointer_only_for_licence":5,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/temporally-distributed-networks-for-fast","title":"Temporally Distributed Networks for Fast Video Semantic Segmentation","date":"2020-04-03","rows_on_this_dataset":3,"code_links":1,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":5,"samples_ran":2,"samples_unverified":3,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/efficient-semantic-video-segmentation-with","title":"Efficient Semantic Video Segmentation with Per-frame Inference","date":"2020-02-26","rows_on_this_dataset":2,"code_links":1,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":3,"samples_ran":1,"samples_unverified":2,"pointer_only_for_licence":3,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/template-based-automatic-search-of-compact","title":"Template-Based Automatic Search of Compact Semantic Segmentation Architectures","date":"2019-04-04","rows_on_this_dataset":2,"code_links":1,"syntology":null},{"paper":"/paper/dfanet-deep-feature-aggregation-for-real-time","title":"DFANet: Deep Feature Aggregation for Real-Time Semantic Segmentation","date":"2019-04-03","rows_on_this_dataset":1,"code_links":2,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":1,"samples_ran":1,"samples_unverified":0,"pointer_only_for_licence":1,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/improving-semantic-segmentation-via-video","title":"Improving Semantic Segmentation via Video Propagation and Label Relaxation","date":"2018-12-04","rows_on_this_dataset":1,"code_links":5,"syntology":null},{"paper":"/paper/efficient-dense-modules-of-asymmetric","title":"Efficient Dense Modules of Asymmetric Convolution for Real-Time Semantic Segmentation","date":"2018-09-17","rows_on_this_dataset":2,"code_links":4,"syntology":null},{"paper":"/paper/efficient-road-lane-marking-detection-with","title":"Efficient Road Lane Marking Detection with Deep Learning","date":"2018-09-11","rows_on_this_dataset":2,"code_links":0,"syntology":null},{"paper":"/paper/bisenet-bilateral-segmentation-network-for","title":"BiSeNet: Bilateral Segmentation Network for Real-time Semantic Segmentation","date":"2018-08-02","rows_on_this_dataset":2,"code_links":21,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":18,"samples_ran":6,"samples_unverified":12,"pointer_only_for_licence":1,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/deep-spatio-temporal-random-fields-for","title":"Deep Spatio-Temporal Random Fields for Efficient Video Segmentation","date":"2018-07-03","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/dense-decoder-shortcut-connections-for-single","title":"Dense Decoder Shortcut Connections for Single-Pass Semantic Segmentation","date":"2018-06-01","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/icnet-for-real-time-semantic-segmentation-on","title":"ICNet for Real-Time Semantic Segmentation on High-Resolution Images","date":"2017-04-27","rows_on_this_dataset":1,"code_links":18,"syntology":null},{"paper":"/paper/semantic-video-segmentation-by-gated","title":"Semantic Video Segmentation by Gated Recurrent Flow Propagation","date":"2016-12-28","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/pyramid-scene-parsing-network","title":"Pyramid Scene Parsing Network","date":"2016-12-04","rows_on_this_dataset":2,"code_links":67,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":29,"samples_ran":7,"samples_unverified":22,"pointer_only_for_licence":5,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/the-one-hundred-layers-tiramisu-fully","title":"The One Hundred Layers Tiramisu: Fully Convolutional DenseNets for Semantic Segmentation","date":"2016-11-28","rows_on_this_dataset":1,"code_links":23,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":24,"samples_ran":1,"samples_unverified":23,"pointer_only_for_licence":6,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/multi-scale-context-aggregation-by-dilated","title":"Multi-Scale Context Aggregation by Dilated Convolutions","date":"2015-11-23","rows_on_this_dataset":2,"code_links":9,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":8,"samples_ran":2,"samples_unverified":6,"pointer_only_for_licence":2,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/reseg-a-recurrent-neural-network-based-model","title":"ReSeg: A Recurrent Neural Network-based Model for Semantic Segmentation","date":"2015-11-22","rows_on_this_dataset":1,"code_links":5,"syntology":null},{"paper":"/paper/segnet-a-deep-convolutional-encoder-decoder","title":"SegNet: A Deep Convolutional Encoder-Decoder Architecture for Image Segmentation","date":"2015-11-02","rows_on_this_dataset":2,"code_links":74,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":44,"samples_ran":9,"samples_unverified":35,"pointer_only_for_licence":10,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/semantic-image-segmentation-with-deep","title":"Semantic Image Segmentation with Deep Convolutional Nets and Fully Connected CRFs","date":"2014-12-22","rows_on_this_dataset":2,"code_links":18,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":1,"samples_ran":0,"samples_unverified":1,"pointer_only_for_licence":1,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}}],"syntology_totals":{"read_at":"2026-09-24T18:15:14+00:00","papers_with_samples":11,"samples_harvested":162,"samples_ran":36,"samples_unverified":126,"pointer_only_for_licence":35,"papers_with_no_sample_that_ran":1,"note":"the per-paper counts above, summed; not a rate"},"papers_note":"The archive never published its papers-using-dataset list; these are papers with a leaderboard row on this dataset's benchmarks."}