Pith. sign in

REVIEW 4 cited by

Frankenstein: Generating Semantic-Compositional 3D Scenes in One Tri-Plane

Not yet reviewed by Pith; the record is open.

Re-run · record.json Download PDF Read on arXiv ↗

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2403.16210 v2 pith:4GDX3Y3M submitted 2024-03-24 cs.CV cs.AIcs.GR

Han Yan , Yang Li , Zhennan Wu , Shenzhou Chen , Weixuan Sun , Taizhang Shang , Weizhe Liu , Tian Chen
show 4 more authors
Xiaqiang Dai Chao Ma Hongdong Li Pan Ji
This is my paper · ORCID
classification cs.CVcs.AIcs.GR
keywords frankensteinscenessinglecompositionalgeneratingmultipleroomsemantic-compositional
verification ladder T0 review T1 audit T2 compute T3 formal

Signed reviews

No signed human review yet.

0 comments
read the original abstract

We present Frankenstein, a diffusion-based framework that can generate semantic-compositional 3D scenes in a single pass. Unlike existing methods that output a single, unified 3D shape, Frankenstein simultaneously generates multiple separated shapes, each corresponding to a semantically meaningful part. The 3D scene information is encoded in one single tri-plane tensor, from which multiple Singed Distance Function (SDF) fields can be decoded to represent the compositional shapes. During training, an auto-encoder compresses tri-planes into a latent space, and then the denoising diffusion process is employed to approximate the distribution of the compositional scenes. Frankenstein demonstrates promising results in generating room interiors as well as human avatars with automatically separated parts. The generated scenes facilitate many downstream applications, such as part-wise re-texturing, object rearrangement in the room or avatar cloth re-targeting. Our project page is available at: https://wolfball.github.io/frankenstein/.

Discussion (0). Continue with ORCID to comment.

Forward citations

Cited by 4 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score. Full citation record

  1. BAG: Body-Aligned 3D Wearable Asset Generation

    cs.CV 2025-01 conditional novelty 6.0 of 10

    BAG generates body-aligned 3D wearable assets from a single image by conditioning multi-view diffusion on canonical body XYZ maps and refining alignment with Sim(3) optimization and physics simulation.

  2. SceneFactor: Factored Latent 3D Diffusion for Controllable 3D Scene Generation

    cs.CV 2024-12 conditional novelty 6.0 of 10

    A two-stage latent diffusion method for text-guided 3D scene generation where a coarse semantic box layout is generated first and then used to condition high-fidelity geometry, enabling localized box-based editing.

  3. PhyCAGE: Physically Plausible Compositional 3D Asset Generation from a Single Image

    cs.CV 2024-11 conditional novelty 6.0 of 10

    A single-image pipeline that generates physically plausible compositional 3D Gaussian Splatting assets by using a physics simulator as a gradient-driven optimizer.

  4. MMGDreamer: Mixed-Modality Graph for Geometry-Controllable 3D Indoor Scene Generation

    cs.CV 2025-02 conditional novelty 5.0 of 10

    MMGDreamer generates 3D indoor scenes from a mixed-modality scene graph whose nodes can be text, images, or both, and it predicts missing object relationships for more coherent layouts.

Pith tools