{"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/pizza-a-powerful-image-only-zero-shot-zero","title":"PIZZA: A Powerful Image-only Zero-Shot Zero-CAD Approach to 6 DoF Tracking","arxiv_id":"2209.07589","date":"2022-09-15","proceeding":null,"authors":["Van Nguyen Nguyen","Yuming Du","Yang Xiao","Michael Ramamonjisoa","Vincent Lepetit"],"abstract":"Estimating the relative pose of a new object without prior knowledge is a hard problem, while it is an ability very much needed in robotics and Augmented Reality. We present a method for tracking the 6D motion of objects in RGB video sequences when neither the training images nor the 3D geometry of the objects are available. In contrast to previous works, our method can therefore consider unknown objects in open world instantly, without requiring any prior information or a specific training phase. We consider two architectures, one based on two frames, and the other relying on a Transformer Encoder, which can exploit an arbitrary number of past frames. We train our architectures using only synthetic renderings with domain randomization. Our results on challenging datasets are on par with previous works that require much more information (training images of the target objects, 3D models, and/or depth data). Our source code is available at https://github.com/nv-nguyen/pizza","url_abs":"https://arxiv.org/abs/2209.07589v2","url_pdf":"https://arxiv.org/pdf/2209.07589v2.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":"pizza-a-powerful-image-only-zero-shot-zero","repo_url":"https://github.com/nv-nguyen/pizza","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"3d-geometry","task_name":"3D geometry"}],"methods":[{"method_slug":"absolute-position-encodings","method_name":"Absolute Position Encodings"},{"method_slug":"adam","method_name":"Adam"},{"method_slug":"attention","method_name":"Attention"},{"method_slug":"bpe","method_name":"BPE"},{"method_slug":"dense-connections","method_name":"Dense Connections"},{"method_slug":"dropout","method_name":"Dropout"},{"method_slug":"label-smoothing","method_name":"Label Smoothing"},{"method_slug":"layer-normalization","method_name":"Layer Normalization"},{"method_slug":"linear-layer","method_name":"Linear Layer"},{"method_slug":"multi-head-attention","method_name":"Multi-Head Attention"},{"method_slug":"position-wise-feed-forward-layer","method_name":"Position-Wise Feed-Forward Layer"},{"method_slug":"residual-connection","method_name":"Residual Connection"},{"method_slug":"softmax","method_name":"Softmax"},{"method_slug":"transformer","method_name":"Transformer"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2209.07589","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2209.07589"}},"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/nv-nguyen/pizza","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"ran":3,"ran_draft_wrong":2,"unverified":13},"by_repo_kind":{"official":{"samples":18,"ran":5,"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":"cad594317b0f657a","entry":"conv1x1","repo":"nv-nguyen/pizza","repo_kind":"official","path":"lib/model/model_utils.py","file_url":"https://github.com/nv-nguyen/pizza/blob/HEAD/lib/model/model_utils.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":"cad594317b0f657a"}},{"code_sha256_prefix":"fac5364e2f53c6db","entry":"conv3x3","repo":"nv-nguyen/pizza","repo_kind":"official","path":"lib/model/resnet.py","file_url":"https://github.com/nv-nguyen/pizza/blob/HEAD/lib/model/resnet.py","link_basis":"harvester_set","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"fac5364e2f53c6db"}},{"code_sha256_prefix":"029098c0420861da","entry":"matrix_to_quaternion","repo":"nv-nguyen/pizza","repo_kind":"official","path":"lib/losses/rotation_conversions.py","file_url":"https://github.com/nv-nguyen/pizza/blob/HEAD/lib/losses/rotation_conversions.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":"029098c0420861da"}},{"code_sha256_prefix":"bec37e39340a8433","entry":"quat2mat","repo":"nv-nguyen/pizza","repo_kind":"official","path":"lib/losses/utils.py","file_url":"https://github.com/nv-nguyen/pizza/blob/HEAD/lib/losses/utils.py","link_basis":"harvester_set","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"bec37e39340a8433"}},{"code_sha256_prefix":"000b3a2e5186a974","entry":"quaternion_to_matrix","repo":"nv-nguyen/pizza","repo_kind":"official","path":"lib/losses/rotation_conversions.py","file_url":"https://github.com/nv-nguyen/pizza/blob/HEAD/lib/losses/rotation_conversions.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":"000b3a2e5186a974"}},{"code_sha256_prefix":"6af97e8f5454cbe7","entry":"apply_data_augmentation","repo":"nv-nguyen/pizza","repo_kind":"official","path":"lib/dataloader/augmentation.py","file_url":"https://github.com/nv-nguyen/pizza/blob/HEAD/lib/dataloader/augmentation.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":"6af97e8f5454cbe7"}},{"code_sha256_prefix":"26c05725afdcb279","entry":"apply_data_augmentation_wo_mask","repo":"nv-nguyen/pizza","repo_kind":"official","path":"lib/dataloader/augmentation.py","file_url":"https://github.com/nv-nguyen/pizza/blob/HEAD/lib/dataloader/augmentation.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":"26c05725afdcb279"}},{"code_sha256_prefix":"1ddc2a9e8a022da9","entry":"apply_data_augmentation_wo_mask_w_erosion","repo":"nv-nguyen/pizza","repo_kind":"official","path":"lib/dataloader/augmentation.py","file_url":"https://github.com/nv-nguyen/pizza/blob/HEAD/lib/dataloader/augmentation.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":"1ddc2a9e8a022da9"}},{"code_sha256_prefix":"edd07560bf716b5d","entry":"batch_rodrigues","repo":"nv-nguyen/pizza","repo_kind":"official","path":"lib/losses/utils.py","file_url":"https://github.com/nv-nguyen/pizza/blob/HEAD/lib/losses/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":"edd07560bf716b5d"}},{"code_sha256_prefix":"3cf617e0b6e54333","entry":"conv3x3","repo":"nv-nguyen/pizza","repo_kind":"official","path":"lib/model/model_utils.py","file_url":"https://github.com/nv-nguyen/pizza/blob/HEAD/lib/model/model_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":"3cf617e0b6e54333"}},{"code_sha256_prefix":"acad9ecc614262ae","entry":"cum_product","repo":"nv-nguyen/pizza","repo_kind":"official","path":"lib/losses/utils.py","file_url":"https://github.com/nv-nguyen/pizza/blob/HEAD/lib/losses/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":"acad9ecc614262ae"}},{"code_sha256_prefix":"5700344447cd559e","entry":"euler_angles_to_matrix","repo":"nv-nguyen/pizza","repo_kind":"official","path":"lib/losses/rotation_conversions.py","file_url":"https://github.com/nv-nguyen/pizza/blob/HEAD/lib/losses/rotation_conversions.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":"5700344447cd559e"}},{"code_sha256_prefix":"01c9842ad89d0266","entry":"init_dataloader","repo":"nv-nguyen/pizza","repo_kind":"official","path":"lib/dataloader/utils.py","file_url":"https://github.com/nv-nguyen/pizza/blob/HEAD/lib/dataloader/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":"01c9842ad89d0266"}},{"code_sha256_prefix":"219905b6f4220fa6","entry":"normalize","repo":"nv-nguyen/pizza","repo_kind":"official","path":"lib/dataloader/image_utils.py","file_url":"https://github.com/nv-nguyen/pizza/blob/HEAD/lib/dataloader/image_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":"219905b6f4220fa6"}},{"code_sha256_prefix":"c9e04d671dc253f4","entry":"open_image","repo":"nv-nguyen/pizza","repo_kind":"official","path":"lib/dataloader/image_utils.py","file_url":"https://github.com/nv-nguyen/pizza/blob/HEAD/lib/dataloader/image_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":"c9e04d671dc253f4"}},{"code_sha256_prefix":"b8db3bdd8b37989c","entry":"resize_pad","repo":"nv-nguyen/pizza","repo_kind":"official","path":"lib/dataloader/image_utils.py","file_url":"https://github.com/nv-nguyen/pizza/blob/HEAD/lib/dataloader/image_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":"b8db3bdd8b37989c"}},{"code_sha256_prefix":"a8b99e29594b0407","entry":"resnet18","repo":"nv-nguyen/pizza","repo_kind":"official","path":"lib/model/resnet.py","file_url":"https://github.com/nv-nguyen/pizza/blob/HEAD/lib/model/resnet.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":"a8b99e29594b0407"}},{"code_sha256_prefix":"51bb2205b42b38e1","entry":"resnet34","repo":"nv-nguyen/pizza","repo_kind":"official","path":"lib/model/resnet.py","file_url":"https://github.com/nv-nguyen/pizza/blob/HEAD/lib/model/resnet.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":"51bb2205b42b38e1"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}