{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:4NWOGRIWRKHCBKRBNJ7IMI5HWQ","short_pith_number":"pith:4NWOGRIW","schema_version":"1.0","canonical_sha256":"e36ce345168a8e20aa216a7e8623a7b406aa7fba247cf731d938f3d776433dd8","source":{"kind":"arxiv","id":"2404.09758","version":2},"attestation_state":"computed","paper":{"title":"Transforming a Non-Differentiable Rasterizer into a Differentiable One with Stochastic Gradient Estimation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.GR","authors_text":"Eric Heitz, Laurent Belcour, Thomas Deliot","submitted_at":"2024-04-15T13:00:09Z","abstract_excerpt":"We show how to transform a non-differentiable rasterizer into a differentiable one with minimal engineering efforts and no external dependencies (no Pytorch/Tensorflow). We rely on Stochastic Gradient Estimation, a technique that consists of rasterizing after randomly perturbing the scene's parameters such that their gradient can be stochastically estimated and descended. This method is simple and robust but does not scale in dimensionality (number of scene parameters). Our insight is that the number of parameters contributing to a given rasterized pixel is bounded. Estimating and averaging gr"},"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":"2404.09758","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.GR","submitted_at":"2024-04-15T13:00:09Z","cross_cats_sorted":[],"title_canon_sha256":"b0ab30574fc8e9890793c8eda948ea36ef59b1873cbeb558e71dfda8f399ffde","abstract_canon_sha256":"b68808bc7ed9b97e4c05dea4e4fd288d2d14b7017872de2c4df89c41c5ce484e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:08:57.946836Z","signature_b64":"Vh1s8JU7BVxgViCIVc40XQ9BXR6PDlBhHcTjp3FPzXSxFUtyyse0A69FDOMEpj5Vvfej7gflxUFqUrtuQEvoCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e36ce345168a8e20aa216a7e8623a7b406aa7fba247cf731d938f3d776433dd8","last_reissued_at":"2026-07-05T08:08:57.946351Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:08:57.946351Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Transforming a Non-Differentiable Rasterizer into a Differentiable One with Stochastic Gradient Estimation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.GR","authors_text":"Eric Heitz, Laurent Belcour, Thomas Deliot","submitted_at":"2024-04-15T13:00:09Z","abstract_excerpt":"We show how to transform a non-differentiable rasterizer into a differentiable one with minimal engineering efforts and no external dependencies (no Pytorch/Tensorflow). We rely on Stochastic Gradient Estimation, a technique that consists of rasterizing after randomly perturbing the scene's parameters such that their gradient can be stochastically estimated and descended. This method is simple and robust but does not scale in dimensionality (number of scene parameters). Our insight is that the number of parameters contributing to a given rasterized pixel is bounded. Estimating and averaging gr"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2404.09758","kind":"arxiv","version":2},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2404.09758/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"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":"2404.09758","created_at":"2026-07-05T08:08:57.946410+00:00"},{"alias_kind":"arxiv_version","alias_value":"2404.09758v2","created_at":"2026-07-05T08:08:57.946410+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2404.09758","created_at":"2026-07-05T08:08:57.946410+00:00"},{"alias_kind":"pith_short_12","alias_value":"4NWOGRIWRKHC","created_at":"2026-07-05T08:08:57.946410+00:00"},{"alias_kind":"pith_short_16","alias_value":"4NWOGRIWRKHCBKRB","created_at":"2026-07-05T08:08:57.946410+00:00"},{"alias_kind":"pith_short_8","alias_value":"4NWOGRIW","created_at":"2026-07-05T08:08:57.946410+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.28622","citing_title":"Meshtryoshka: Differentiable Rendering of Real-World Scenes via Mesh Rasterization","ref_index":47,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/4NWOGRIWRKHCBKRBNJ7IMI5HWQ","json":"https://pith.science/pith/4NWOGRIWRKHCBKRBNJ7IMI5HWQ.json","graph_json":"https://pith.science/api/pith-number/4NWOGRIWRKHCBKRBNJ7IMI5HWQ/graph.json","events_json":"https://pith.science/api/pith-number/4NWOGRIWRKHCBKRBNJ7IMI5HWQ/events.json","paper":"https://pith.science/paper/4NWOGRIW"},"agent_actions":{"view_html":"https://pith.science/pith/4NWOGRIWRKHCBKRBNJ7IMI5HWQ","download_json":"https://pith.science/pith/4NWOGRIWRKHCBKRBNJ7IMI5HWQ.json","view_paper":"https://pith.science/paper/4NWOGRIW","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2404.09758&json=true","fetch_graph":"https://pith.science/api/pith-number/4NWOGRIWRKHCBKRBNJ7IMI5HWQ/graph.json","fetch_events":"https://pith.science/api/pith-number/4NWOGRIWRKHCBKRBNJ7IMI5HWQ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/4NWOGRIWRKHCBKRBNJ7IMI5HWQ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/4NWOGRIWRKHCBKRBNJ7IMI5HWQ/action/storage_attestation","attest_author":"https://pith.science/pith/4NWOGRIWRKHCBKRBNJ7IMI5HWQ/action/author_attestation","sign_citation":"https://pith.science/pith/4NWOGRIWRKHCBKRBNJ7IMI5HWQ/action/citation_signature","submit_replication":"https://pith.science/pith/4NWOGRIWRKHCBKRBNJ7IMI5HWQ/action/replication_record"}},"created_at":"2026-07-05T08:08:57.946410+00:00","updated_at":"2026-07-05T08:08:57.946410+00:00"}