{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/mobilestereonet-towards-lightweight-deep","title":"MobileStereoNet: Towards Lightweight Deep Networks for Stereo Matching","arxiv_id":"2108.09770","date":"2021-08-22","proceeding":null,"authors":["Faranak Shamsafar","Samuel Woerz","Rafia Rahim","Andreas Zell"],"abstract":"Recent methods in stereo matching have continuously improved the accuracy using deep models. This gain, however, is attained with a high increase in computation cost, such that the network may not fit even on a moderate GPU. This issue raises problems when the model needs to be deployed on resource-limited devices. For this, we propose two light models for stereo vision with reduced complexity and without sacrificing accuracy. Depending on the dimension of cost volume, we design a 2D and a 3D model with encoder-decoders built from 2D and 3D convolutions, respectively. To this end, we leverage 2D MobileNet blocks and extend them to 3D for stereo vision application. Besides, a new cost volume is proposed to boost the accuracy of the 2D model, making it performing close to 3D networks. Experiments show that the proposed 2D/3D networks effectively reduce the computational expense (27%/95% and 72%/38% fewer parameters/operations in 2D and 3D models, respectively) while upholding the accuracy. Our code is available at https://github.com/cogsys-tuebingen/mobilestereonet.","url_abs":"https://arxiv.org/abs/2108.09770v1","url_pdf":"https://arxiv.org/pdf/2108.09770v1.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"mobilestereonet-towards-lightweight-deep","repo_url":"https://github.com/cogsys-tuebingen/mobilestereonet","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"mobilestereonet-towards-lightweight-deep","repo_url":"https://github.com/UCI-ISA-Lab/MultiHeadDepth-HomoDepth","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"mobilestereonet-towards-lightweight-deep","repo_url":"https://github.com/ibaiGorordo/ONNX-MobileStereoNet","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"mobilestereonet-towards-lightweight-deep","repo_url":"https://github.com/ibaiGorordo/TFLite-MobileStereoNet","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"depth-estimation","task_name":"Depth Estimation"},{"task_slug":"disparity-estimation","task_name":"Disparity Estimation"},{"task_slug":null,"task_name":"GPU"},{"task_slug":"stereo-depth-estimation","task_name":"Stereo Depth Estimation"},{"task_slug":"stereo-matching-1","task_name":"Stereo Matching"}],"methods":[{"method_slug":"1x1-convolution","method_name":"1x1 Convolution"},{"method_slug":"average-pooling","method_name":"Average Pooling"},{"method_slug":"batch-normalization","method_name":"Batch Normalization"},{"method_slug":"convolution","method_name":"Convolution"},{"method_slug":"dense-connections","method_name":"Dense Connections"},{"method_slug":"depthwise-convolution","method_name":"Depthwise Convolution"},{"method_slug":"depthwise-separable-convolution","method_name":"Depthwise Separable Convolution"},{"method_slug":"global-average-pooling","method_name":"Global Average Pooling"},{"method_slug":"inverted-residual-block","method_name":"Inverted Residual Block"},{"method_slug":"mobilenetv1","method_name":"MobileNetV1"},{"method_slug":"pointwise-convolution","method_name":"Pointwise Convolution"},{"method_slug":"relu","method_name":"ReLU"},{"method_slug":"softmax","method_name":"Softmax"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/stereo-depth-estimation-on-kitti2015","task":"Stereo Depth Estimation","dataset":"KITTI2015","model":"3D-MobileStereoNet","rank_in_archive_order":2,"of":7,"metrics":{"three pixel error":"1.69"},"uses_additional_data":false},{"leaderboard":"/sota/stereo-depth-estimation-on-kitti2015","task":"Stereo Depth Estimation","dataset":"KITTI2015","model":"2D-MobileStereoNet","rank_in_archive_order":5,"of":7,"metrics":{"three pixel error":"2.67"},"uses_additional_data":false},{"leaderboard":"/sota/stereo-depth-estimation-on-sceneflow","task":"Stereo Depth Estimation","dataset":"sceneflow","model":"3D-MobileStereoNet","rank_in_archive_order":1,"of":3,"metrics":{"Average End-Point Error":"0.80","EPE":"0.80"},"uses_additional_data":false},{"leaderboard":"/sota/stereo-depth-estimation-on-sceneflow","task":"Stereo Depth Estimation","dataset":"sceneflow","model":"2D-MobileStereoNet","rank_in_archive_order":3,"of":3,"metrics":{"Average End-Point Error":"1.14","EPE":"1.14"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2108.09770","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2108.09770"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-24T18:15:14+00:00","read_at_is":"when the build read Syntology's graph, not when any sample ran","claim":"Per-sample execution status on synthesized fixtures; not a correctness claim about the paper. Samples come from repositories linked to the paper, official or community; repo_kind says which.","repos":[{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/ibaiGorordo/ONNX-MobileStereoNet","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/ibaiGorordo/TFLite-MobileStereoNet","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/UCI-ISA-Lab/MultiHeadDepth-HomoDepth","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/cogsys-tuebingen/mobilestereonet","reach":null}],"summary":{"ran_draft_wrong":1,"unverified":7},"by_repo_kind":{"official":{"samples":1,"ran":1,"repositories":1},"listed":{"samples":7,"ran":0,"repositories":2}},"repo_kind_vocabulary":{"official":"The archive marks this repository official for the paper","named_in_paper":"The archive records that the paper mentions this repository; it is not marked official","listed":"In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper","found_in_text":"Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted","community":"Not in the archive's code links for this paper; a community repository Syntology harvested"},"n_pointer_only_for_licence":0,"samples":[{"code_sha256_prefix":"5e310fcb52fdb183","entry":"input_constructor","repo":"cogsys-tuebingen/mobilestereonet","repo_kind":"official","path":"cost.py","file_url":"https://github.com/cogsys-tuebingen/mobilestereonet/blob/HEAD/cost.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"5e310fcb52fdb183"}},{"code_sha256_prefix":"9d919b029837f9f6","entry":"draw_depth","repo":"ibaiGorordo/ONNX-MobileStereoNet","repo_kind":"listed","path":"mobilestereonet/utils.py","file_url":"https://github.com/ibaiGorordo/ONNX-MobileStereoNet/blob/HEAD/mobilestereonet/utils.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"9d919b029837f9f6"}},{"code_sha256_prefix":"f1e3085f00b12eed","entry":"draw_disparity","repo":"ibaiGorordo/ONNX-MobileStereoNet","repo_kind":"listed","path":"mobilestereonet/utils.py","file_url":"https://github.com/ibaiGorordo/ONNX-MobileStereoNet/blob/HEAD/mobilestereonet/utils.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"f1e3085f00b12eed"}},{"code_sha256_prefix":"e87d661ef8163fd0","entry":"efficient_blk","repo":"UCI-ISA-Lab/MultiHeadDepth-HomoDepth","repo_kind":"listed","path":"model.py","file_url":"https://github.com/UCI-ISA-Lab/MultiHeadDepth-HomoDepth/blob/HEAD/model.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"e87d661ef8163fd0"}},{"code_sha256_prefix":"b79a2825facd8942","entry":"feature_fusion","repo":"UCI-ISA-Lab/MultiHeadDepth-HomoDepth","repo_kind":"listed","path":"model.py","file_url":"https://github.com/UCI-ISA-Lab/MultiHeadDepth-HomoDepth/blob/HEAD/model.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"b79a2825facd8942"}},{"code_sha256_prefix":"78ab4a5f6d826cb2","entry":"gard_map","repo":"UCI-ISA-Lab/MultiHeadDepth-HomoDepth","repo_kind":"listed","path":"utils.py","file_url":"https://github.com/UCI-ISA-Lab/MultiHeadDepth-HomoDepth/blob/HEAD/utils.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"78ab4a5f6d826cb2"}},{"code_sha256_prefix":"04b60886e9a88a2d","entry":"img2tensor","repo":"UCI-ISA-Lab/MultiHeadDepth-HomoDepth","repo_kind":"listed","path":"utils.py","file_url":"https://github.com/UCI-ISA-Lab/MultiHeadDepth-HomoDepth/blob/HEAD/utils.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"04b60886e9a88a2d"}},{"code_sha256_prefix":"a8f2a79258b4f21b","entry":"readPFM","repo":"UCI-ISA-Lab/MultiHeadDepth-HomoDepth","repo_kind":"listed","path":"utils.py","file_url":"https://github.com/UCI-ISA-Lab/MultiHeadDepth-HomoDepth/blob/HEAD/utils.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"a8f2a79258b4f21b"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}