{"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/spidepth-strengthened-pose-information-for","title":"SPIdepth: Strengthened Pose Information for Self-supervised Monocular Depth Estimation","arxiv_id":"2404.12501","date":"2024-04-18","proceeding":null,"authors":["Mykola Lavreniuk"],"abstract":"Self-supervised monocular depth estimation has garnered considerable attention for its applications in autonomous driving and robotics. While recent methods have made strides in leveraging techniques like the Self Query Layer (SQL) to infer depth from motion, they often overlook the potential of strengthening pose information. In this paper, we introduce SPIdepth, a novel approach that prioritizes enhancing the pose network for improved depth estimation. Building upon the foundation laid by SQL, SPIdepth emphasizes the importance of pose information in capturing fine-grained scene structures. By enhancing the pose network's capabilities, SPIdepth achieves remarkable advancements in scene understanding and depth estimation. Experimental results on benchmark datasets such as KITTI, Cityscapes, and Make3D showcase SPIdepth's state-of-the-art performance, surpassing previous methods by significant margins. Specifically, SPIdepth tops the self-supervised KITTI benchmark. Additionally, SPIdepth achieves the lowest AbsRel (0.029), SqRel (0.069), and RMSE (1.394) on KITTI, establishing new state-of-the-art results. On Cityscapes, SPIdepth shows improvements over SQLdepth of 21.7% in AbsRel, 36.8% in SqRel, and 16.5% in RMSE, even without using motion masks. On Make3D, SPIdepth in zero-shot outperforms all other models. Remarkably, SPIdepth achieves these results using only a single image for inference, surpassing even methods that utilize video sequences for inference, thus demonstrating its efficacy and efficiency in real-world applications. Our approach represents a significant leap forward in self-supervised monocular depth estimation, underscoring the importance of strengthening pose information for advancing scene understanding in real-world applications. The code and pre-trained models are publicly available at https://github.com/Lavreniuk/SPIdepth.","url_abs":"https://arxiv.org/abs/2404.12501v3","url_pdf":"https://arxiv.org/pdf/2404.12501v3.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":"spidepth-strengthened-pose-information-for","repo_url":"https://github.com/Lavreniuk/SPIdepth","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"autonomous-driving","task_name":"Autonomous Driving"},{"task_slug":"depth-estimation","task_name":"Depth Estimation"},{"task_slug":"monocular-depth-estimation","task_name":"Monocular Depth Estimation"},{"task_slug":"scene-understanding","task_name":"Scene Understanding"},{"task_slug":"unsupervised-monocular-depth-estimation","task_name":"Unsupervised Monocular Depth Estimation"}],"methods":[{"method_slug":"attention","method_name":"Attention"},{"method_slug":"linear-layer","method_name":"Linear Layer"},{"method_slug":"multi-head-attention","method_name":"Multi-Head Attention"},{"method_slug":"transformer","method_name":"Transformer"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/monocular-depth-estimation-on-kitti-eigen","task":"Monocular Depth Estimation","dataset":"KITTI Eigen split","model":"SPIDepth","rank_in_archive_order":1,"of":79,"metrics":{"Delta < 1.25":"0.99","Delta < 1.25^2":"0.999","Delta < 1.25^3":"1.000","RMSE":"1.394","RMSE log":"0.048","Sq Rel":"0.069","absolute relative error":"0.029"},"uses_additional_data":true},{"leaderboard":"/sota/monocular-depth-estimation-on-kitti-eigen-1","task":"Monocular Depth Estimation","dataset":"KITTI Eigen split unsupervised","model":"SPIdepth","rank_in_archive_order":1,"of":55,"metrics":{"Delta < 1.25":"0.94","Delta < 1.25^2":"0.973","Delta < 1.25^3":"0.985","Mono":"X","RMSE":"3.662","RMSE log":"0.153","Resolution":"1024x320","Sq Rel":"0.531","Test frames":"1","absolute relative error":"0.071"},"uses_additional_data":false},{"leaderboard":"/sota/monocular-depth-estimation-on-make3d","task":"Monocular Depth Estimation","dataset":"Make3D","model":"SPIDepth","rank_in_archive_order":1,"of":6,"metrics":{"Abs Rel":"0.299","RMSE":"6.672","Sq Rel":"1.931"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2404.12501","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2404.12501"}},"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/Lavreniuk/SPIdepth","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"ran_violates":1,"ran_fixture":1,"ran":9,"ran_honours":1,"ran_draft_wrong":1,"unverified":1},"by_repo_kind":{"official":{"samples":14,"ran":13,"repositories":1}},"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":"94402f271c35bec0","entry":"gray2rgb","repo":"Lavreniuk/SPIdepth","repo_kind":"official","path":"CKA_visualize.py","file_url":"https://github.com/Lavreniuk/SPIdepth/blob/HEAD/CKA_visualize.py","link_basis":"plan_row","language":"python","status":"ran_violates","verification_level":2,"contract_check":"VIOLATES","metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"94402f271c35bec0"}},{"code_sha256_prefix":"a8814cc5c348b987","entry":"batch_post_process_disparity","repo":"Lavreniuk/SPIdepth","repo_kind":"official","path":"evaluate_depth_config.py","file_url":"https://github.com/Lavreniuk/SPIdepth/blob/HEAD/evaluate_depth_config.py","link_basis":"harvester_set","language":"python","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"a8814cc5c348b987"}},{"code_sha256_prefix":"d2ebd83bfabb3603","entry":"cls_padding","repo":"Lavreniuk/SPIdepth","repo_kind":"official","path":"CKA_visualize.py","file_url":"https://github.com/Lavreniuk/SPIdepth/blob/HEAD/CKA_visualize.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"d2ebd83bfabb3603"}},{"code_sha256_prefix":"edd4f86e8f02732f","entry":"compute_errors","repo":"Lavreniuk/SPIdepth","repo_kind":"official","path":"evaluate_depth_config.py","file_url":"https://github.com/Lavreniuk/SPIdepth/blob/HEAD/evaluate_depth_config.py","link_basis":"harvester_set","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"edd4f86e8f02732f"}},{"code_sha256_prefix":"acb6c7be50a85a77","entry":"compute_errors","repo":"Lavreniuk/SPIdepth","repo_kind":"official","path":"finetune/evaluate_metric_depth.py","file_url":"https://github.com/Lavreniuk/SPIdepth/blob/HEAD/finetune/evaluate_metric_depth.py","link_basis":"plan_row","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"acb6c7be50a85a77"}},{"code_sha256_prefix":"fcd63b56aa65b0a4","entry":"convert_R3x3t1x3_to_Transform4x4","repo":"Lavreniuk/SPIdepth","repo_kind":"official","path":"layers.py","file_url":"https://github.com/Lavreniuk/SPIdepth/blob/HEAD/layers.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"fcd63b56aa65b0a4"}},{"code_sha256_prefix":"89177c685e07c0df","entry":"denormalize","repo":"Lavreniuk/SPIdepth","repo_kind":"official","path":"finetune/evaluate_metric_depth.py","file_url":"https://github.com/Lavreniuk/SPIdepth/blob/HEAD/finetune/evaluate_metric_depth.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"89177c685e07c0df"}},{"code_sha256_prefix":"62287188376f0ba0","entry":"disp_to_depth","repo":"Lavreniuk/SPIdepth","repo_kind":"official","path":"calc_layers.py","file_url":"https://github.com/Lavreniuk/SPIdepth/blob/HEAD/calc_layers.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"62287188376f0ba0"}},{"code_sha256_prefix":"955112f5788539a8","entry":"get_translation_matrix","repo":"Lavreniuk/SPIdepth","repo_kind":"official","path":"calc_layers.py","file_url":"https://github.com/Lavreniuk/SPIdepth/blob/HEAD/calc_layers.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"955112f5788539a8"}},{"code_sha256_prefix":"b8681e1b096dae74","entry":"highlight_grid","repo":"Lavreniuk/SPIdepth","repo_kind":"official","path":"CKA_visualize.py","file_url":"https://github.com/Lavreniuk/SPIdepth/blob/HEAD/CKA_visualize.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"b8681e1b096dae74"}},{"code_sha256_prefix":"92654d948ee55789","entry":"preprocessing_transforms","repo":"Lavreniuk/SPIdepth","repo_kind":"official","path":"finetune/dataloader.py","file_url":"https://github.com/Lavreniuk/SPIdepth/blob/HEAD/finetune/dataloader.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"92654d948ee55789"}},{"code_sha256_prefix":"faac9130cc118fec","entry":"remove_leading_slash","repo":"Lavreniuk/SPIdepth","repo_kind":"official","path":"finetune/dataloader.py","file_url":"https://github.com/Lavreniuk/SPIdepth/blob/HEAD/finetune/dataloader.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"faac9130cc118fec"}},{"code_sha256_prefix":"cdc03d6bfc4d3a34","entry":"transformation_from_parameters","repo":"Lavreniuk/SPIdepth","repo_kind":"official","path":"calc_layers.py","file_url":"https://github.com/Lavreniuk/SPIdepth/blob/HEAD/calc_layers.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"cdc03d6bfc4d3a34"}},{"code_sha256_prefix":"1781f75a68fc284c","entry":"predict_tta","repo":"Lavreniuk/SPIdepth","repo_kind":"official","path":"finetune/evaluate_metric_depth.py","file_url":"https://github.com/Lavreniuk/SPIdepth/blob/HEAD/finetune/evaluate_metric_depth.py","link_basis":"first_harvest_node","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":"1781f75a68fc284c"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}