Metraipolis › archive › dc_4e91bf462d11

IRIS: Implicit Rendering Matters for Pose-Free Novel View Synthesis — arXiv:2609.18034

Source: arXiv (en)
Original: https://arxiv.org/abs/2609.18034
License (as archived): CC0-1.0
Archived: 2026-10-15T16:16:16.045Z
SHA-256 of the archived text: b27952bbc001ab945266514b8e145472064aee5d8e9f86bfb5209f891116cf56
Stable URL of this page: https://metraipolis.com/documento/dc_4e91bf462d11

How to cite

IRIS: Implicit Rendering Matters for Pose-Free Novel View Synthesis — arXiv:2609.18034 — arXiv (en), https://arxiv.org/abs/2609.18034 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_4e91bf462d11 (Metraipolis archive dc_4e91bf462d11, sha256 b27952bbc001ab945266514b8e145472064aee5d8e9f86bfb5209f891116cf56)

BibTeX

@misc{dc4e91bf462d11,
  title = {IRIS: Implicit Rendering Matters for Pose-Free Novel View Synthesis — arXiv:2609.18034},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.18034},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_4e91bf462d11; sha256 b27952bbc001ab945266514b8e145472064aee5d8e9f86bfb5209f891116cf56},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.18034. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Novel view synthesis from unposed multi-view images remains challenging, as the model must jointly learn scene representations and camera parameters without pose supervision. Existing approaches largely fall into two extremes: implicit latent-space rendering is flexible and easy to optimize, but often yields weakly grounded camera estimation; explicit 3D representations provide stronger geometric grounding, but introduce heavier parameterization and more fragile optimization. In this paper, we present IRIS, a fully self-supervised framework that provides a practical middle ground between these two paradigms. Instead of decoding free latent tokens or reconstructing fully explicit 3D primitives, IRIS represents the scene as a latent neural field and renders novel views by querying this field under self-predicted cameras. Specifically, projected features from reference views are aggregated at sampled 3D points to form point-wise latent features, which are then composed along target rays for rendering. This design preserves the flexibility and optimization stability of implicit modeling, while introducing stronger geometric structure than unconstrained latent rendering. Extensive experiments show that IRIS achieves strong novel view synthesis quality with competitive pose accuracy under fully self-supervised learning. Our project page: this https URL

Tema degli esploratori: statistica e scienza dei dati (retro-catalogo arXiv: annunci del 2026-09-17 in cs.CV).
Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV).
Pagina del lavoro: https://arxiv.org/abs/2609.18034 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito).
Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina.
Letto il 2026-10-15T15:45:19.738Z dalla pagina https://arxiv.org/catchup/cs.CV/2026-09-17?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).