{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2018:POZBQEXHL22DBPLJWVPFLEBJK2","short_pith_number":"pith:POZBQEXH","canonical_record":{"source":{"id":"1811.12328","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2018-11-29T17:27:03Z","cross_cats_sorted":[],"title_canon_sha256":"9d13f581547320b17831003e49aa667d0fbed41e754e9bd9002300c1d9a28888","abstract_canon_sha256":"536ebec18e32a6e7bf37d46b4900dc50988c39237ccb6ec8b45d0bc3945cf5a9"},"schema_version":"1.0"},"canonical_sha256":"7bb21812e75eb430bd69b55e55902956bbd32d20e7deafa031ef300caf858351","source":{"kind":"arxiv","id":"1811.12328","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1811.12328","created_at":"2026-05-17T23:59:33Z"},{"alias_kind":"arxiv_version","alias_value":"1811.12328v1","created_at":"2026-05-17T23:59:33Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1811.12328","created_at":"2026-05-17T23:59:33Z"},{"alias_kind":"pith_short_12","alias_value":"POZBQEXHL22D","created_at":"2026-05-18T12:32:46Z"},{"alias_kind":"pith_short_16","alias_value":"POZBQEXHL22DBPLJ","created_at":"2026-05-18T12:32:46Z"},{"alias_kind":"pith_short_8","alias_value":"POZBQEXH","created_at":"2026-05-18T12:32:46Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2018:POZBQEXHL22DBPLJWVPFLEBJK2","target":"record","payload":{"canonical_record":{"source":{"id":"1811.12328","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2018-11-29T17:27:03Z","cross_cats_sorted":[],"title_canon_sha256":"9d13f581547320b17831003e49aa667d0fbed41e754e9bd9002300c1d9a28888","abstract_canon_sha256":"536ebec18e32a6e7bf37d46b4900dc50988c39237ccb6ec8b45d0bc3945cf5a9"},"schema_version":"1.0"},"canonical_sha256":"7bb21812e75eb430bd69b55e55902956bbd32d20e7deafa031ef300caf858351","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:59:33.761962Z","signature_b64":"XWqxxX9u0nKaiT3cSS9X34v0un0LLhTehE8A9rkv1QpzNgbhJtby4QHq3THtjfSJZfzI8JAoifv0WXXjM3ONDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7bb21812e75eb430bd69b55e55902956bbd32d20e7deafa031ef300caf858351","last_reissued_at":"2026-05-17T23:59:33.761327Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:59:33.761327Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1811.12328","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-17T23:59:33Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"MXHf73z4pilC6jfXnf2vRcjeaF9dMq54H79kU5ZQLLhjBhmanVnx+sTJqae+1slEY6M96XK7lkqVnp3/L8XCBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-19T22:44:07.568358Z"},"content_sha256":"c0a3644276df8201a262f6c2292b7f49f94838d834cbf8ae0b0e3d988fc33366","schema_version":"1.0","event_id":"sha256:c0a3644276df8201a262f6c2292b7f49f94838d834cbf8ae0b0e3d988fc33366"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2018:POZBQEXHL22DBPLJWVPFLEBJK2","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"InverseRenderNet: Learning single image inverse rendering","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"William A. P. Smith, Ye Yu","submitted_at":"2018-11-29T17:27:03Z","abstract_excerpt":"We show how to train a fully convolutional neural network to perform inverse rendering from a single, uncontrolled image. The network takes an RGB image as input, regresses albedo and normal maps from which we compute lighting coefficients. Our network is trained using large uncontrolled image collections without ground truth. By incorporating a differentiable renderer, our network can learn from self-supervision. Since the problem is ill-posed we introduce additional supervision: 1. We learn a statistical natural illumination prior, 2. Our key insight is to perform offline multiview stereo (M"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1811.12328","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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-17T23:59:33Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"DuqijGNRkGtDuTof9ko3tHcK/kk1KTUKZ14t4bkzS8EXF4LiMpxZMNR1MpZ3xGj2o2eaJFp2DuMGwgeW8ow1BQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-19T22:44:07.568707Z"},"content_sha256":"0615a2beef8d827b8da2c792fa91662c1a2938dce08a02a1d30b37c126cbfc51","schema_version":"1.0","event_id":"sha256:0615a2beef8d827b8da2c792fa91662c1a2938dce08a02a1d30b37c126cbfc51"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/POZBQEXHL22DBPLJWVPFLEBJK2/bundle.json","state_url":"https://pith.science/pith/POZBQEXHL22DBPLJWVPFLEBJK2/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/POZBQEXHL22DBPLJWVPFLEBJK2/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-05-19T22:44:07Z","links":{"resolver":"https://pith.science/pith/POZBQEXHL22DBPLJWVPFLEBJK2","bundle":"https://pith.science/pith/POZBQEXHL22DBPLJWVPFLEBJK2/bundle.json","state":"https://pith.science/pith/POZBQEXHL22DBPLJWVPFLEBJK2/state.json","well_known_bundle":"https://pith.science/.well-known/pith/POZBQEXHL22DBPLJWVPFLEBJK2/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2018:POZBQEXHL22DBPLJWVPFLEBJK2","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"536ebec18e32a6e7bf37d46b4900dc50988c39237ccb6ec8b45d0bc3945cf5a9","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2018-11-29T17:27:03Z","title_canon_sha256":"9d13f581547320b17831003e49aa667d0fbed41e754e9bd9002300c1d9a28888"},"schema_version":"1.0","source":{"id":"1811.12328","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1811.12328","created_at":"2026-05-17T23:59:33Z"},{"alias_kind":"arxiv_version","alias_value":"1811.12328v1","created_at":"2026-05-17T23:59:33Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1811.12328","created_at":"2026-05-17T23:59:33Z"},{"alias_kind":"pith_short_12","alias_value":"POZBQEXHL22D","created_at":"2026-05-18T12:32:46Z"},{"alias_kind":"pith_short_16","alias_value":"POZBQEXHL22DBPLJ","created_at":"2026-05-18T12:32:46Z"},{"alias_kind":"pith_short_8","alias_value":"POZBQEXH","created_at":"2026-05-18T12:32:46Z"}],"graph_snapshots":[{"event_id":"sha256:0615a2beef8d827b8da2c792fa91662c1a2938dce08a02a1d30b37c126cbfc51","target":"graph","created_at":"2026-05-17T23:59:33Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"paper":{"abstract_excerpt":"We show how to train a fully convolutional neural network to perform inverse rendering from a single, uncontrolled image. The network takes an RGB image as input, regresses albedo and normal maps from which we compute lighting coefficients. Our network is trained using large uncontrolled image collections without ground truth. By incorporating a differentiable renderer, our network can learn from self-supervision. Since the problem is ill-posed we introduce additional supervision: 1. We learn a statistical natural illumination prior, 2. Our key insight is to perform offline multiview stereo (M","authors_text":"William A. P. Smith, Ye Yu","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2018-11-29T17:27:03Z","title":"InverseRenderNet: Learning single image inverse rendering"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1811.12328","kind":"arxiv","version":1},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:c0a3644276df8201a262f6c2292b7f49f94838d834cbf8ae0b0e3d988fc33366","target":"record","created_at":"2026-05-17T23:59:33Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"536ebec18e32a6e7bf37d46b4900dc50988c39237ccb6ec8b45d0bc3945cf5a9","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2018-11-29T17:27:03Z","title_canon_sha256":"9d13f581547320b17831003e49aa667d0fbed41e754e9bd9002300c1d9a28888"},"schema_version":"1.0","source":{"id":"1811.12328","kind":"arxiv","version":1}},"canonical_sha256":"7bb21812e75eb430bd69b55e55902956bbd32d20e7deafa031ef300caf858351","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"7bb21812e75eb430bd69b55e55902956bbd32d20e7deafa031ef300caf858351","first_computed_at":"2026-05-17T23:59:33.761327Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:59:33.761327Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"XWqxxX9u0nKaiT3cSS9X34v0un0LLhTehE8A9rkv1QpzNgbhJtby4QHq3THtjfSJZfzI8JAoifv0WXXjM3ONDQ==","signature_status":"signed_v1","signed_at":"2026-05-17T23:59:33.761962Z","signed_message":"canonical_sha256_bytes"},"source_id":"1811.12328","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:c0a3644276df8201a262f6c2292b7f49f94838d834cbf8ae0b0e3d988fc33366","sha256:0615a2beef8d827b8da2c792fa91662c1a2938dce08a02a1d30b37c126cbfc51"],"state_sha256":"ec8a7869d50ffe4e08772d1c6bfdc96662ac28d100610337767507361daf87da"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"2VepilMASY1GN6QRH2kRTowHImCGKuQ0E2smpJ9JqFzqZ7SDJ1RILcpFkLbx+8Yr0uz7nmwmoKFJUCd9MZ0oAA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-19T22:44:07.570895Z","bundle_sha256":"28c42a884c96f08d85185aecfb3f6e17108a89031e11941c635e17e74a969709"}}