{"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/from-big-to-small-multi-scale-local-planar","title":"From Big to Small: Multi-Scale Local Planar Guidance for Monocular Depth Estimation","arxiv_id":"1907.10326","date":"2019-07-24","proceeding":null,"authors":["Jin Han Lee","Myung-Kyu Han","Dong Wook Ko","Il Hong Suh"],"abstract":"Estimating accurate depth from a single image is challenging because it is an ill-posed problem as infinitely many 3D scenes can be projected to the same 2D scene. However, recent works based on deep convolutional neural networks show great progress with plausible results. The convolutional neural networks are generally composed of two parts: an encoder for dense feature extraction and a decoder for predicting the desired depth. In the encoder-decoder schemes, repeated strided convolution and spatial pooling layers lower the spatial resolution of transitional outputs, and several techniques such as skip connections or multi-layer deconvolutional networks are adopted to recover the original resolution for effective dense prediction. In this paper, for more effective guidance of densely encoded features to the desired depth prediction, we propose a network architecture that utilizes novel local planar guidance layers located at multiple stages in the decoding phase. We show that the proposed method outperforms the state-of-the-art works with significant margin evaluating on challenging benchmarks. We also provide results from an ablation study to validate the effectiveness of the proposed method.","url_abs":"https://arxiv.org/abs/1907.10326v6","url_pdf":"https://arxiv.org/pdf/1907.10326v6.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":"from-big-to-small-multi-scale-local-planar","repo_url":"https://github.com/cogaplex-bts/bts","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok","spdx":"GPL-3.0"}},{"paper_slug":"from-big-to-small-multi-scale-local-planar","repo_url":"https://github.com/AbhinavAtrishi/semisupervised-multitask-learning","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}},{"paper_slug":"from-big-to-small-multi-scale-local-planar","repo_url":"https://github.com/Navhkrin/Bts-PyTorch","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"from-big-to-small-multi-scale-local-planar","repo_url":"https://github.com/ShuweiShao/NDDepth","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"from-big-to-small-multi-scale-local-planar","repo_url":"https://github.com/TWJianNuo/EdgeDepth-Release","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"from-big-to-small-multi-scale-local-planar","repo_url":"https://github.com/cleinc/bts","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"GPL-3.0"}},{"paper_slug":"from-big-to-small-multi-scale-local-planar","repo_url":"https://github.com/jiao0805/bts4","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok","spdx":"GPL-3.0"}},{"paper_slug":"from-big-to-small-multi-scale-local-planar","repo_url":"https://github.com/ku-cvlab/maskingdepth","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"from-big-to-small-multi-scale-local-planar","repo_url":"https://github.com/lakshjaisinghani/pseudo-lidar-pipeline","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"gone","observed_at":"2026-09-17","how":"tree_404+repo_404"}},{"paper_slug":"from-big-to-small-multi-scale-local-planar","repo_url":"https://github.com/lakshjaisinghani/pseudo-lidar-ros-pipeline","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"gone","observed_at":"2026-09-17","how":"tree_404+repo_404"}},{"paper_slug":"from-big-to-small-multi-scale-local-planar","repo_url":"https://github.com/northeastsquare/bts","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":null},{"paper_slug":"from-big-to-small-multi-scale-local-planar","repo_url":"https://github.com/rnlee1998/bts","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"GPL-3.0"}},{"paper_slug":"from-big-to-small-multi-scale-local-planar","repo_url":"https://github.com/saeid-h/bts-fully-tf","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":null},{"paper_slug":"from-big-to-small-multi-scale-local-planar","repo_url":"https://github.com/shuweishao/iebins","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"decoder","task_name":"Decoder"},{"task_slug":"depth-estimation","task_name":"Depth Estimation"},{"task_slug":"depth-prediction","task_name":"Depth Prediction"},{"task_slug":"monocular-depth-estimation","task_name":"Monocular Depth Estimation"}],"methods":[{"method_slug":"convolution","method_name":"Convolution"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/depth-estimation-on-nyu-depth-v2","task":"Depth Estimation","dataset":"NYU-Depth V2","model":"BTS","rank_in_archive_order":9,"of":17,"metrics":{"RMS":"0.407"},"uses_additional_data":false},{"leaderboard":"/sota/monocular-depth-estimation-on-kitti-eigen","task":"Monocular Depth Estimation","dataset":"KITTI Eigen split","model":"BTS","rank_in_archive_order":39,"of":79,"metrics":{"absolute relative error":"0.064"},"uses_additional_data":false},{"leaderboard":"/sota/monocular-depth-estimation-on-nyu-depth-v2","task":"Monocular Depth Estimation","dataset":"NYU-Depth V2","model":"BTS","rank_in_archive_order":61,"of":85,"metrics":{"Delta < 1.25^3":"0.995","RMSE":"0.392"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1907.10326","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1907.10326"}},"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/cleinc/bts","reach":{"status":"ok","spdx":"GPL-3.0"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/jiao0805/bts4","reach":{"status":"ok","spdx":"GPL-3.0"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/cogaplex-bts/bts","reach":{"status":"ok","spdx":"GPL-3.0"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/shuweishao/iebins","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/lakshjaisinghani/pseudo-lidar-ros-pipeline","reach":{"status":"gone","observed_at":"2026-09-17","how":"tree_404+repo_404"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/rnlee1998/bts","reach":{"status":"ok","spdx":"GPL-3.0"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/lakshjaisinghani/pseudo-lidar-pipeline","reach":{"status":"gone","observed_at":"2026-09-17","how":"tree_404+repo_404"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/northeastsquare/bts","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/TWJianNuo/EdgeDepth-Release","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/saeid-h/bts-fully-tf","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/AbhinavAtrishi/semisupervised-multitask-learning","reach":{"status":"ok"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/Navhkrin/Bts-PyTorch","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/ShuweiShao/NDDepth","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/ku-cvlab/maskingdepth","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"ran_honours":2,"ran":3,"unverified":10},"by_repo_kind":{"official":{"samples":1,"ran":1,"repositories":1},"listed":{"samples":14,"ran":4,"repositories":4}},"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":4,"samples":[{"code_sha256_prefix":"0a6b6b2f73096252","entry":"compute_errors","repo":"cogaplex-bts/bts","repo_kind":"official","path":"pytorch/bts_eval.py","file_url":"https://github.com/cogaplex-bts/bts/blob/HEAD/pytorch/bts_eval.py","link_basis":"plan_row","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"GPL-3.0","inline_ok":false,"mcp_get_code":{"code_sha256":"0a6b6b2f73096252"}},{"code_sha256_prefix":"62287188376f0ba0","entry":"disp_to_depth","repo":"ku-cvlab/maskingdepth","repo_kind":"listed","path":"layers.py","file_url":"https://github.com/ku-cvlab/maskingdepth/blob/HEAD/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":"050c56fb7282eb88","entry":"get_num_lines","repo":"northeastsquare/bts","repo_kind":"listed","path":"bts_test.py","file_url":"https://github.com/northeastsquare/bts/blob/HEAD/bts_test.py","link_basis":"first_harvest_node","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"well_formed","behaviour_fingerprint":false,"licence":"GPL-3.0","inline_ok":false,"mcp_get_code":{"code_sha256":"050c56fb7282eb88"}},{"code_sha256_prefix":"955112f5788539a8","entry":"get_translation_matrix","repo":"ku-cvlab/maskingdepth","repo_kind":"listed","path":"layers.py","file_url":"https://github.com/ku-cvlab/maskingdepth/blob/HEAD/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":"cdc03d6bfc4d3a34","entry":"transformation_from_parameters","repo":"ku-cvlab/maskingdepth","repo_kind":"listed","path":"layers.py","file_url":"https://github.com/ku-cvlab/maskingdepth/blob/HEAD/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":"e082c0223082e9e0","entry":"KittiDataLoader","repo":"Navhkrin/Bts-PyTorch","repo_kind":"listed","path":"KittiDataLoader.py","file_url":"https://github.com/Navhkrin/Bts-PyTorch/blob/HEAD/KittiDataLoader.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":"e082c0223082e9e0"}},{"code_sha256_prefix":"49f623fef46f4164","entry":"build_tensors_in_checkpoint_file","repo":"northeastsquare/bts","repo_kind":"listed","path":"bts_main.py","file_url":"https://github.com/northeastsquare/bts/blob/HEAD/bts_main.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"GPL-3.0","inline_ok":false,"mcp_get_code":{"code_sha256":"49f623fef46f4164"}},{"code_sha256_prefix":"63ca4a7a3dc39918","entry":"eval","repo":"saeid-h/bts-fully-tf","repo_kind":"listed","path":"eval_with_pngs.py","file_url":"https://github.com/saeid-h/bts-fully-tf/blob/HEAD/eval_with_pngs.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"GPL-3.0","inline_ok":false,"mcp_get_code":{"code_sha256":"63ca4a7a3dc39918"}},{"code_sha256_prefix":"8d1b07ca0bd8236f","entry":"gaussian","repo":"ku-cvlab/maskingdepth","repo_kind":"listed","path":"kernels.py","file_url":"https://github.com/ku-cvlab/maskingdepth/blob/HEAD/kernels.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":"8d1b07ca0bd8236f"}},{"code_sha256_prefix":"fbbad6fe724c704a","entry":"gaussian_discrete_erf","repo":"ku-cvlab/maskingdepth","repo_kind":"listed","path":"kernels.py","file_url":"https://github.com/ku-cvlab/maskingdepth/blob/HEAD/kernels.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":"fbbad6fe724c704a"}},{"code_sha256_prefix":"82c88408427b2989","entry":"get_readout_oper","repo":"ku-cvlab/maskingdepth","repo_kind":"listed","path":"networks/dpt_utils.py","file_url":"https://github.com/ku-cvlab/maskingdepth/blob/HEAD/networks/dpt_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":"82c88408427b2989"}},{"code_sha256_prefix":"dedc460d0c6214a1","entry":"make_fusion_block","repo":"ku-cvlab/maskingdepth","repo_kind":"listed","path":"networks/dpt_utils.py","file_url":"https://github.com/ku-cvlab/maskingdepth/blob/HEAD/networks/dpt_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":"dedc460d0c6214a1"}},{"code_sha256_prefix":"432b3087fed580c3","entry":"make_scratch","repo":"ku-cvlab/maskingdepth","repo_kind":"listed","path":"networks/dpt_utils.py","file_url":"https://github.com/ku-cvlab/maskingdepth/blob/HEAD/networks/dpt_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":"432b3087fed580c3"}},{"code_sha256_prefix":"6ee3f3744ec86804","entry":"model_forward","repo":"ku-cvlab/maskingdepth","repo_kind":"listed","path":"loss.py","file_url":"https://github.com/ku-cvlab/maskingdepth/blob/HEAD/loss.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":"6ee3f3744ec86804"}},{"code_sha256_prefix":"2d3c0858ee51aa88","entry":"normalize_kernel2d","repo":"ku-cvlab/maskingdepth","repo_kind":"listed","path":"kernels.py","file_url":"https://github.com/ku-cvlab/maskingdepth/blob/HEAD/kernels.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":"2d3c0858ee51aa88"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}