ANTI-AI ARCHIVE
ART-HISTORY NODE / 304 · 2024-12-02

Structured 3D Latents for Scalable and Versatile 3D Generation

Structured 3D Latents for Scalable and Versatile 3D Generation

Xiang, Jianfeng; Lv, Zelong; Xu, Sicheng; Deng, Yu; Wang, Ruicheng; Zhang, Bowen; Chen, Dong; Tong, Xin; Yang, Jiaolong

Introduction

TRELLIS uses structured latents to connect text or image conditions with meshes, radiance fields and Gaussians, examining representation and editability in 3D asset generation.

ORIGINAL DOCUMENT#304
Figure 1: TRELLIS assets in different 3D formats, conditioned on images or text, and local edits.View full image ↗

Figure 1: TRELLIS assets in different 3D formats, conditioned on images or text, and local edits. Source: v3; the image version is distinct from the initial submission date.

Xiang, Jianfeng; Lv, Zelong; Xu, Sicheng; Deng, Yu; Wang, Ruicheng; Zhang, Bowen; Chen, Dong; Tong, Xin; Yang, Jiaolong · 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 · Structured 3D Latents for Scalable and Versatile 3D Generation ↗

RESEARCH ACCOUNT

TRELLIS uses structured latents to connect text or image conditions with meshes, radiance fields and Gaussians, examining representation and editability in 3D asset generation.

ANTI-AI ARCHIVE · Revised 2026-10-03

What the paper investigates

SLAT combines a sparse 3D grid with multiview visual features, carrying structural and appearance information. Rectified-flow transformers generate in this representation, which can be decoded into multiple formats and supports local editing.

Section sources: Structured 3D Latents for Scalable and Versatile 3D Generation

Its place in generative-art history

Editorial interpretation: output format and editability determine which production pipelines can use a result. The entry preserves the difference between obtaining a three-dimensional-looking image and receiving an asset that can be further processed.

Section sources: Structured 3D Latents for Scalable and Versatile 3D Generation

Reading limits and versions

Multiple output formats do not guarantee suitable topology, materials or manufacturability; demonstrations do not replace project-specific validation.

Section sources: Structured 3D Latents for Scalable and Versatile 3D Generation

Sources for this account

Structured 3D Latents for Scalable and Versatile 3D Generation ↗

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

3D Gaussian Splatting for Real-Time Radiance Field Rendering ↗

TRELLIS: compare methods, control or evaluation conditions with 3D Gaussian Splatting.

DreamFusion: Text-to-3D using 2D Diffusion ↗

TRELLIS: compare methods, control or evaluation conditions with DreamFusion.

Dream Machine ↗

TRELLIS: compare methods, control or evaluation conditions with Dream Machine.

FLUX.1 model family ↗

TRELLIS: compare methods, control or evaluation conditions with A new model ecosystem.

Dates & version record

Date displayed for this node: 2024-12-02 · Historical date recorded for the source: 2024-12-02

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 v3; 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.

01
Structured 3D Latents for Scalable and Versatile 3D Generation ↗

Structured 3D Latents for Scalable and Versatile 3D Generation

https://arxiv.org/abs/2412.01506

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 #304 · 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. · 029
Date as recorded: 2024-12-02
Structured 3D Latents for Scalable and Versatile 3D Generation ↗
Structured 3D Latents for Scalable and Versatile 3D Generation

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. Structured 3D Latents for Scalable and Versatile 3D Generation. Art-history node #304. https://salondesrefuses.cn/en/art-history/352

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.