{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2017:GPKBQDHD3J7H7UARRLWGACSFZA","short_pith_number":"pith:GPKBQDHD","schema_version":"1.0","canonical_sha256":"33d4180ce3da7e7fd0118aec600a45c82a4b27c677aaa460487c805ddfb081c0","source":{"kind":"arxiv","id":"1707.02937","version":1},"attestation_state":"computed","paper":{"title":"Checkerboard artifact free sub-pixel convolution: A note on sub-pixel convolution, resize convolution and convolution resize","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Andrew Aitken, Christian Ledig, Jose Caballero, Lucas Theis, Wenzhe Shi, Zehan Wang","submitted_at":"2017-07-10T16:41:22Z","abstract_excerpt":"The most prominent problem associated with the deconvolution layer is the presence of checkerboard artifacts in output images and dense labels. To combat this problem, smoothness constraints, post processing and different architecture designs have been proposed. Odena et al. highlight three sources of checkerboard artifacts: deconvolution overlap, random initialization and loss functions. In this note, we proposed an initialization method for sub-pixel convolution known as convolution NN resize. Compared to sub-pixel convolution initialized with schemes designed for standard convolution kernel"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"1707.02937","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2017-07-10T16:41:22Z","cross_cats_sorted":[],"title_canon_sha256":"372a88559e7426c1a16778512d9f2ebade6b50646873bc47cfc8330bacc5d6b6","abstract_canon_sha256":"5f15f3807e516ce4ae3c14312d1cf64fb1d387dd2d72e279c2a061d4fb7719b8"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:40:35.405377Z","signature_b64":"WsUMHl823Jz68yLpIbZNnb+ZJGfpK5s41svJALJrRn9LFIoW+bNqFGZEPdomJR5ywcLStGUv9BNYOSOnCjlDAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"33d4180ce3da7e7fd0118aec600a45c82a4b27c677aaa460487c805ddfb081c0","last_reissued_at":"2026-05-18T00:40:35.404721Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:40:35.404721Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Checkerboard artifact free sub-pixel convolution: A note on sub-pixel convolution, resize convolution and convolution resize","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Andrew Aitken, Christian Ledig, Jose Caballero, Lucas Theis, Wenzhe Shi, Zehan Wang","submitted_at":"2017-07-10T16:41:22Z","abstract_excerpt":"The most prominent problem associated with the deconvolution layer is the presence of checkerboard artifacts in output images and dense labels. To combat this problem, smoothness constraints, post processing and different architecture designs have been proposed. Odena et al. highlight three sources of checkerboard artifacts: deconvolution overlap, random initialization and loss functions. In this note, we proposed an initialization method for sub-pixel convolution known as convolution NN resize. Compared to sub-pixel convolution initialized with schemes designed for standard convolution kernel"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1707.02937","kind":"arxiv","version":1},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"aliases":[{"alias_kind":"arxiv","alias_value":"1707.02937","created_at":"2026-05-18T00:40:35.404821+00:00"},{"alias_kind":"arxiv_version","alias_value":"1707.02937v1","created_at":"2026-05-18T00:40:35.404821+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1707.02937","created_at":"2026-05-18T00:40:35.404821+00:00"},{"alias_kind":"pith_short_12","alias_value":"GPKBQDHD3J7H","created_at":"2026-05-18T12:31:18.294218+00:00"},{"alias_kind":"pith_short_16","alias_value":"GPKBQDHD3J7H7UAR","created_at":"2026-05-18T12:31:18.294218+00:00"},{"alias_kind":"pith_short_8","alias_value":"GPKBQDHD","created_at":"2026-05-18T12:31:18.294218+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2605.15895","citing_title":"Layer Selection in Feature-Based Losses Affects Image Quality and Microstructural Consistency in Deep Learning Super-Resolution of Brain Diffusion MRI","ref_index":39,"is_internal_anchor":true},{"citing_arxiv_id":"2604.21681","citing_title":"Sapiens2","ref_index":2,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/GPKBQDHD3J7H7UARRLWGACSFZA","json":"https://pith.science/pith/GPKBQDHD3J7H7UARRLWGACSFZA.json","graph_json":"https://pith.science/api/pith-number/GPKBQDHD3J7H7UARRLWGACSFZA/graph.json","events_json":"https://pith.science/api/pith-number/GPKBQDHD3J7H7UARRLWGACSFZA/events.json","paper":"https://pith.science/paper/GPKBQDHD"},"agent_actions":{"view_html":"https://pith.science/pith/GPKBQDHD3J7H7UARRLWGACSFZA","download_json":"https://pith.science/pith/GPKBQDHD3J7H7UARRLWGACSFZA.json","view_paper":"https://pith.science/paper/GPKBQDHD","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1707.02937&json=true","fetch_graph":"https://pith.science/api/pith-number/GPKBQDHD3J7H7UARRLWGACSFZA/graph.json","fetch_events":"https://pith.science/api/pith-number/GPKBQDHD3J7H7UARRLWGACSFZA/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/GPKBQDHD3J7H7UARRLWGACSFZA/action/timestamp_anchor","attest_storage":"https://pith.science/pith/GPKBQDHD3J7H7UARRLWGACSFZA/action/storage_attestation","attest_author":"https://pith.science/pith/GPKBQDHD3J7H7UARRLWGACSFZA/action/author_attestation","sign_citation":"https://pith.science/pith/GPKBQDHD3J7H7UARRLWGACSFZA/action/citation_signature","submit_replication":"https://pith.science/pith/GPKBQDHD3J7H7UARRLWGACSFZA/action/replication_record"}},"created_at":"2026-05-18T00:40:35.404821+00:00","updated_at":"2026-05-18T00:40:35.404821+00:00"}