{"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/a-closer-look-at-invariances-in-self","title":"A Closer Look at Invariances in Self-supervised Pre-training for 3D Vision","arxiv_id":"2207.04997","date":"2022-07-11","proceeding":null,"authors":["Lanxiao Li","Michael Heizmann"],"abstract":"Self-supervised pre-training for 3D vision has drawn increasing research interest in recent years. In order to learn informative representations, a lot of previous works exploit invariances of 3D features, e.g., perspective-invariance between views of the same scene, modality-invariance between depth and RGB images, format-invariance between point clouds and voxels. Although they have achieved promising results, previous researches lack a systematic and fair comparison of these invariances. To address this issue, our work, for the first time, introduces a unified framework, under which various pre-training methods can be investigated. We conduct extensive experiments and provide a closer look at the contributions of different invariances in 3D pre-training. Also, we propose a simple but effective method that jointly pre-trains a 3D encoder and a depth map encoder using contrastive learning. Models pre-trained with our method gain significant performance boost in downstream tasks. For instance, a pre-trained VoteNet outperforms previous methods on SUN RGB-D and ScanNet object detection benchmarks with a clear margin.","url_abs":"https://arxiv.org/abs/2207.04997v2","url_pdf":"https://arxiv.org/pdf/2207.04997v2.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":"a-closer-look-at-invariances-in-self","repo_url":"https://github.com/lilanxiao/invar3d","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"contrastive-learning","task_name":"Contrastive Learning"},{"task_slug":"object-detection","task_name":"Object Detection"},{"task_slug":"object-detection-1","task_name":"object-detection"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":null,"atlas_url":"https://app.syntology.ai/?focus=2207.04997","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2207.04997"}},"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/lilanxiao/invar3d","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"ran":1,"unverified":11},"by_repo_kind":{"listed":{"samples":12,"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":"8cacb1e15bf1d910","entry":"concat_all_gather","repo":"lilanxiao/invar3d","repo_kind":"listed","path":"loss_moco.py","file_url":"https://github.com/lilanxiao/invar3d/blob/HEAD/loss_moco.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":"8cacb1e15bf1d910"}},{"code_sha256_prefix":"ad25233af6c3d190","entry":"batch_shuffle_ddp","repo":"lilanxiao/invar3d","repo_kind":"listed","path":"loss_moco.py","file_url":"https://github.com/lilanxiao/invar3d/blob/HEAD/loss_moco.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":"ad25233af6c3d190"}},{"code_sha256_prefix":"756e7cffdd4b7f0a","entry":"contrast_in_bacth","repo":"lilanxiao/invar3d","repo_kind":"listed","path":"loss.py","file_url":"https://github.com/lilanxiao/invar3d/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":"756e7cffdd4b7f0a"}},{"code_sha256_prefix":"c9d418ddc1cfc9c2","entry":"contrast_in_scene","repo":"lilanxiao/invar3d","repo_kind":"listed","path":"loss.py","file_url":"https://github.com/lilanxiao/invar3d/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":"c9d418ddc1cfc9c2"}},{"code_sha256_prefix":"ab15951e35e67a98","entry":"depth2points","repo":"lilanxiao/invar3d","repo_kind":"listed","path":"scannet/data_utils.py","file_url":"https://github.com/lilanxiao/invar3d/blob/HEAD/scannet/data_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":"ab15951e35e67a98"}},{"code_sha256_prefix":"4fe4c96dd9f15ede","entry":"gather_normalize_2d3d","repo":"lilanxiao/invar3d","repo_kind":"listed","path":"loss.py","file_url":"https://github.com/lilanxiao/invar3d/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":"4fe4c96dd9f15ede"}},{"code_sha256_prefix":"a93412e4a677be68","entry":"get_split","repo":"lilanxiao/invar3d","repo_kind":"listed","path":"scannet/sampler.py","file_url":"https://github.com/lilanxiao/invar3d/blob/HEAD/scannet/sampler.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":"a93412e4a677be68"}},{"code_sha256_prefix":"b74158904f710a22","entry":"global_features","repo":"lilanxiao/invar3d","repo_kind":"listed","path":"loss_moco.py","file_url":"https://github.com/lilanxiao/invar3d/blob/HEAD/loss_moco.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":"b74158904f710a22"}},{"code_sha256_prefix":"0d36479bd8145ff0","entry":"read_scannet_instri","repo":"lilanxiao/invar3d","repo_kind":"listed","path":"scannet/data_utils.py","file_url":"https://github.com/lilanxiao/invar3d/blob/HEAD/scannet/data_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":"0d36479bd8145ff0"}},{"code_sha256_prefix":"e9a8d842472af519","entry":"remove_zeros","repo":"lilanxiao/invar3d","repo_kind":"listed","path":"scannet/data_utils.py","file_url":"https://github.com/lilanxiao/invar3d/blob/HEAD/scannet/data_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":"e9a8d842472af519"}},{"code_sha256_prefix":"b9c584cfcb20e22d","entry":"revert_depth","repo":"lilanxiao/invar3d","repo_kind":"listed","path":"scannet/depth_histogram.py","file_url":"https://github.com/lilanxiao/invar3d/blob/HEAD/scannet/depth_histogram.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":"b9c584cfcb20e22d"}},{"code_sha256_prefix":"4f5254c26b3f5bfb","entry":"sample","repo":"lilanxiao/invar3d","repo_kind":"listed","path":"scannet/sampler.py","file_url":"https://github.com/lilanxiao/invar3d/blob/HEAD/scannet/sampler.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":"4f5254c26b3f5bfb"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}