Metraipolis › archive › dc_e2ed3bb10d68

Stabilizing Camera-Controlled Novel View Synthesis at Inference Time — arXiv:2609.03639

Source: arXiv (en)
Original: https://arxiv.org/abs/2609.03639
License (as archived): CC0-1.0
Archived: 2026-10-17T02:56:22.697Z
SHA-256 of the archived text: 2eac6ae43554d07314f1816cd2249bf3e2b110fdfb6a3fa9d900cc55ebc11cd1
Stable URL of this page: https://metraipolis.com/documento/dc_e2ed3bb10d68

How to cite

Stabilizing Camera-Controlled Novel View Synthesis at Inference Time — arXiv:2609.03639 — arXiv (en), https://arxiv.org/abs/2609.03639 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_e2ed3bb10d68 (Metraipolis archive dc_e2ed3bb10d68, sha256 2eac6ae43554d07314f1816cd2249bf3e2b110fdfb6a3fa9d900cc55ebc11cd1)

BibTeX

@misc{dce2ed3bb10d68,
  title = {Stabilizing Camera-Controlled Novel View Synthesis at Inference Time — arXiv:2609.03639},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.03639},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_e2ed3bb10d68; sha256 2eac6ae43554d07314f1816cd2249bf3e2b110fdfb6a3fa9d900cc55ebc11cd1},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.03639. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Training-free, camera-controlled novel view synthesis from a single image using pre-trained video diffusion models often becomes unstable under large camera motion and long generation horizons. Existing approaches commonly combine several inference-time components, making it unclear which design choices are most important for stability. We show that the main source of stability is simple. Decomposing camera motion into small autoregressive steps limits per-step geometric distortion and reduces error accumulation. A controlled camera-step study shows that performance remains stable for small motions and degrades more strongly as the per-step motion approaches $18$-$20^\circ$. We further evaluate geometry-constrained spatial attention and low-frequency appearance anchoring as supporting refinements, together with an efficient registration-free warping pipeline. Across RealEstate10K and MegaScene, CamTrol++ improves temporal and geometric consistency, downstream 3D reconstruction quality, and generation efficiency over training-free baselines. The method remains effective for 56-frame generation and under substantial controlled depth corruption. These results show that careful control of camera motion at inference time can substantially improve the stability of camera-controlled novel view synthesis without retraining or modifying the diffusion backbone.

Tema degli esploratori: statistica e scienza dei dati (retro-catalogo arXiv: annunci del 2026-09-04 in cs.CV).
Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV).
Pagina del lavoro: https://arxiv.org/abs/2609.03639 — 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 2026-10-17T02:27:18.977Z dalla pagina https://arxiv.org/catchup/cs.CV/2026-09-04?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).