Introduction
Zero-1-to-3 conditions novel views on a single image and a relative camera change, connecting image priors with 3D reconstruction while exposing the problem of inferred unseen surfaces.
View full image ↗Figure 1: single-image inputs and synthesised views after camera changes. Source: v1; the image version is distinct from the initial submission date.
Liu, Ruoshi; Wu, Rundi; Van Hoorick, Basile; Tokmakov, Pavel; Zakharov, Sergey; Vondrick, Carl · original paper / arXiv · Rights in the paper and depicted works remain with their holders. Research quotation does not establish an open licence; republication rights await independent review.
Source · Zero-1-to-3: Zero-shot One Image to 3D Object ↗RESEARCH ACCOUNT
Zero-1-to-3 conditions novel views on a single image and a relative camera change, connecting image priors with 3D reconstruction while exposing the problem of inferred unseen surfaces.
ANTI-AI ARCHIVE · Revised 2026-10-03
What the paper investigates
Synthetic training data teaches relative camera control while pretrained diffusion priors support generalisation to new inputs. The paper demonstrates both novel-view synthesis and single-image reconstruction built on it, including inputs outside ordinary product photographs.
Section sources: Zero-1-to-3: Zero-shot One Image to 3D Object
Its place in generative-art history
Editorial interpretation: an image becomes a starting point for a viewable object, but unseen surfaces are inferred. For artworks, heritage objects and archival images, that inference should remain distinguishable from measured reconstruction.
Section sources: Zero-1-to-3: Zero-shot One Image to 3D Object
Reading limits and versions
Single-view reconstruction is underconstrained: plausible appearance does not establish that inferred geometry or rear surfaces exist in reality.
Section sources: Zero-1-to-3: Zero-shot One Image to 3D Object
Sources for this account
Read the arXiv abstract, authors and version history, plus the selected figure/page on PDF page 1; proofs and full experiments were not independently audited.
Read the arXiv abstract, authors and version history, plus the selected figure/page on PDF page 1; proofs and full experiments were not independently audited. The account and translation are AI-assisted, pending independent human review. Section references identify evidence without claiming independent verification of every historical statement.
Continue with a comparative question
Zero-1-to-3: compare methods, control or evaluation conditions with DreamFusion.
Zero-1-to-3: compare methods, control or evaluation conditions with TRELLIS.
Zero-1-to-3: compare methods, control or evaluation conditions with Dream Machine.
Zero-1-to-3: compare methods, control or evaluation conditions with From images to video.
Dates & version record
Date displayed for this node: 2023-03-20 · Historical date recorded for the source: 2023-03-20
The timeline uses the initial arXiv submission, distinct from conference publication, model release and the archive addition on 3 October 2026. The account and image refer to v1; its date is recorded in the source history.
These dates refer to the historical event or recorded version, not this page’s publication date. The original date precision and unresolved questions are retained.
Original sources & further reading
These links lead to the cited paper, article, institution or conference page. External texts retain their source languages.
Zero-1-to-3: Zero-shot One Image to 3D Object
https://arxiv.org/abs/2303.11328
Current cited URL
Read the arXiv abstract, authors and version history, plus the selected figure/page on PDF page 1; proofs and full experiments were not independently audited.
Provenance, translation & verification
Archive node #222 · Initial research-paper submission; methods, evaluation and production conditions
Research materials & supplement references · 1
Recent research papers: additions and reconciled sources since 2022 · Read the arXiv abstract, authors and version history, plus the selected figure/page on PDF page 1; proofs and full experiments were not independently audited. · 016
Date as recorded: 2023-03-20
Zero-1-to-3: Zero-shot One Image to 3D Object ↗
Zero-1-to-3: Zero-shot One Image to 3D Object
Archive account based on the listed research materials, not a full translation of the linked work. AI-assisted translation; independent human review pending.
Official material was read within the stated scope; see the source note for reading limits and outstanding checks.
Cite this node
ANTI-AI ARCHIVE. Zero-1-to-3: Zero-shot One Image to 3D Object. Art-history node #222. https://salondesrefuses.cn/en/art-history/339
For specific historical claims, also cite the original sources above and include your access date. This account is not a full translation of the linked work.
Adjacent nodes follow chronological order; adjacency does not establish direct influence or causation.