{"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/learning-so3-equivariant-representations-with","title":"Learning SO(3) Equivariant Representations with Spherical CNNs","arxiv_id":"1711.06721","date":"2017-11-17","proceeding":"ECCV 2018 9","authors":["Carlos Esteves","Christine Allen-Blanchette","Ameesh Makadia","Kostas Daniilidis"],"abstract":"We address the problem of 3D rotation equivariance in convolutional neural\nnetworks. 3D rotations have been a challenging nuisance in 3D classification\ntasks requiring higher capacity and extended data augmentation in order to\ntackle it. We model 3D data with multi-valued spherical functions and we\npropose a novel spherical convolutional network that implements exact\nconvolutions on the sphere by realizing them in the spherical harmonic domain.\nResulting filters have local symmetry and are localized by enforcing smooth\nspectra. We apply a novel pooling on the spectral domain and our operations are\nindependent of the underlying spherical resolution throughout the network. We\nshow that networks with much lower capacity and without requiring data\naugmentation can exhibit performance comparable to the state of the art in\nstandard retrieval and classification benchmarks.","url_abs":"http://arxiv.org/abs/1711.06721v3","url_pdf":"http://arxiv.org/pdf/1711.06721v3.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":"learning-so3-equivariant-representations-with","repo_url":"https://github.com/daniilidis-group/spherical-cnn","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"tf","reach":null},{"paper_slug":"learning-so3-equivariant-representations-with","repo_url":"https://github.com/aidinhass/tf-sphcnn","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"unanswered"}},{"paper_slug":"learning-so3-equivariant-representations-with","repo_url":"https://github.com/google-research/spherical-cnn","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"jax","reach":null}],"tasks":[{"task_slug":"3d-classification","task_name":"3D Classification"},{"task_slug":"data-augmentation","task_name":"Data Augmentation"},{"task_slug":"classification","task_name":"General Classification"},{"task_slug":"retrieval","task_name":"Retrieval"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1711.06721","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1711.06721"}},"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/daniilidis-group/spherical-cnn","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/aidinhass/tf-sphcnn","reach":{"status":"unanswered"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/google-research/spherical-cnn","reach":null}],"summary":{"ran_honours":1,"ran_draft_wrong":1},"by_repo_kind":{"official":{"samples":1,"ran":1,"repositories":1},"listed":{"samples":1,"ran":1,"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":"f834f8aa37090ae9","entry":"dup","repo":"daniilidis-group/spherical-cnn","repo_kind":"official","path":"spherical_cnn/models.py","file_url":"https://github.com/daniilidis-group/spherical-cnn/blob/HEAD/spherical_cnn/models.py","link_basis":"first_harvest_node","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":"f834f8aa37090ae9"}},{"code_sha256_prefix":"58ca6105b81d5686","entry":"get_zero_nonzero_idx","repo":"google-research/spherical-cnn","repo_kind":"listed","path":"spherical_cnn/layers.py","file_url":"https://github.com/google-research/spherical-cnn/blob/HEAD/spherical_cnn/layers.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":"58ca6105b81d5686"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}