{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:AZQN6YDDFHW3HAFXPHT4UAREAD","short_pith_number":"pith:AZQN6YDD","schema_version":"1.0","canonical_sha256":"0660df606329edb380b779e7ca022400c92e671c648366c00f04271014bbab12","source":{"kind":"arxiv","id":"2607.02515","version":1},"attestation_state":"computed","paper":{"title":"PointDiT: Pixel-Space Diffusion for Monocular Geometry Estimation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Andreas Geiger, Fabian Manhardt, Federico Tombari, Haofei Xu, Marc Pollefeys, Michael Niemeyer, Michael Oechsle, Nikolai Kalischek, Philipp Henzler, Rundi Wu","submitted_at":"2026-07-02T17:59:56Z","abstract_excerpt":"State-of-the-art single-image 3D reconstruction methods often rely on complex hybrid architectures and loss functions, or compress geometry into latent spaces in order to leverage pre-trained latent diffusion models. In this work, we show that such architectural overhead and intricate loss formulations are unnecessary. We introduce a minimalist pixel-space Diffusion Transformer, built on a plain ViT, that operates directly on raw 3D point map patches and is conditioned on image tokens from a pre-trained DINOv3. Unlike existing latent diffusion approaches, we train our diffusion backbone entire"},"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":"2607.02515","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-07-02T17:59:56Z","cross_cats_sorted":[],"title_canon_sha256":"a419ca2c83c9c049c7c850609b135a6cb03fd59e278dbdbb0f7ebe99d51b810b","abstract_canon_sha256":"293bc5189f5af7550dfae3280b41cc6710f0c9a6656d5c5c9248c86f98b4c42a"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-03T01:18:01.619928Z","signature_b64":"VS7xvRrsDYx8S1lsQf9msTy4gLAn1ekkg+OStbiqWcDFt4g5Ol04IsTXVyrm39Rof7Xk6yaLTFUMszCp7uLmAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0660df606329edb380b779e7ca022400c92e671c648366c00f04271014bbab12","last_reissued_at":"2026-07-03T01:18:01.619569Z","signature_status":"signed_v1","first_computed_at":"2026-07-03T01:18:01.619569Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"PointDiT: Pixel-Space Diffusion for Monocular Geometry Estimation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Andreas Geiger, Fabian Manhardt, Federico Tombari, Haofei Xu, Marc Pollefeys, Michael Niemeyer, Michael Oechsle, Nikolai Kalischek, Philipp Henzler, Rundi Wu","submitted_at":"2026-07-02T17:59:56Z","abstract_excerpt":"State-of-the-art single-image 3D reconstruction methods often rely on complex hybrid architectures and loss functions, or compress geometry into latent spaces in order to leverage pre-trained latent diffusion models. In this work, we show that such architectural overhead and intricate loss formulations are unnecessary. We introduce a minimalist pixel-space Diffusion Transformer, built on a plain ViT, that operates directly on raw 3D point map patches and is conditioned on image tokens from a pre-trained DINOv3. Unlike existing latent diffusion approaches, we train our diffusion backbone entire"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.02515","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2607.02515/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":"2607.02515","created_at":"2026-07-03T01:18:01.619622+00:00"},{"alias_kind":"arxiv_version","alias_value":"2607.02515v1","created_at":"2026-07-03T01:18:01.619622+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.02515","created_at":"2026-07-03T01:18:01.619622+00:00"},{"alias_kind":"pith_short_12","alias_value":"AZQN6YDDFHW3","created_at":"2026-07-03T01:18:01.619622+00:00"},{"alias_kind":"pith_short_16","alias_value":"AZQN6YDDFHW3HAFX","created_at":"2026-07-03T01:18:01.619622+00:00"},{"alias_kind":"pith_short_8","alias_value":"AZQN6YDD","created_at":"2026-07-03T01:18:01.619622+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/AZQN6YDDFHW3HAFXPHT4UAREAD","json":"https://pith.science/pith/AZQN6YDDFHW3HAFXPHT4UAREAD.json","graph_json":"https://pith.science/api/pith-number/AZQN6YDDFHW3HAFXPHT4UAREAD/graph.json","events_json":"https://pith.science/api/pith-number/AZQN6YDDFHW3HAFXPHT4UAREAD/events.json","paper":"https://pith.science/paper/AZQN6YDD"},"agent_actions":{"view_html":"https://pith.science/pith/AZQN6YDDFHW3HAFXPHT4UAREAD","download_json":"https://pith.science/pith/AZQN6YDDFHW3HAFXPHT4UAREAD.json","view_paper":"https://pith.science/paper/AZQN6YDD","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2607.02515&json=true","fetch_graph":"https://pith.science/api/pith-number/AZQN6YDDFHW3HAFXPHT4UAREAD/graph.json","fetch_events":"https://pith.science/api/pith-number/AZQN6YDDFHW3HAFXPHT4UAREAD/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/AZQN6YDDFHW3HAFXPHT4UAREAD/action/timestamp_anchor","attest_storage":"https://pith.science/pith/AZQN6YDDFHW3HAFXPHT4UAREAD/action/storage_attestation","attest_author":"https://pith.science/pith/AZQN6YDDFHW3HAFXPHT4UAREAD/action/author_attestation","sign_citation":"https://pith.science/pith/AZQN6YDDFHW3HAFXPHT4UAREAD/action/citation_signature","submit_replication":"https://pith.science/pith/AZQN6YDDFHW3HAFXPHT4UAREAD/action/replication_record"}},"created_at":"2026-07-03T01:18:01.619622+00:00","updated_at":"2026-07-03T01:18:01.619622+00:00"}