Pith. sign in

REVIEW 5 cited by

REPARO: Compositional 3D Assets Generation with Differentiable 3D Layout Alignment

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 2405.18525 v2 pith:ADZGMUWD submitted 2024-05-28 cs.CV

Haonan Han , Rui Yang , Huan Liao , Jiankai Xing , Zunnan Xu , Xiaoming Yu , Junwei Zha , Xiu Li
show 1 more author
Wanhua Li
This is my paper · ORCID
classification cs.CV
keywords reparoscenedifferentiablegenerationlayoutaddressapproachassets
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

Traditional image-to-3D models often struggle with scenes containing multiple objects due to biases and occlusion complexities. To address this challenge, we present REPARO, a novel approach for compositional 3D asset generation from single images. REPARO employs a two-step process: first, it extracts individual objects from the scene and reconstructs their 3D meshes using off-the-shelf image-to-3D models; then, it optimizes the layout of these meshes through differentiable rendering techniques, ensuring coherent scene composition. By integrating optimal transport-based long-range appearance loss term and high-level semantic loss term in the differentiable rendering, REPARO can effectively recover the layout of 3D assets. The proposed method can significantly enhance object independence, detail accuracy, and overall scene coherence. Extensive evaluation of multi-object scenes demonstrates that our REPARO offers a comprehensive approach to address the complexities of multi-object 3D scene generation from single images.

Discussion (0). Continue with ORCID to comment.

Forward citations

Cited by 5 Pith papers

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

  1. BANG: Dividing 3D Assets via Generative Exploded Dynamics

    cs.GR 2025-07 conditional novelty 7.0 of 10

    A diffusion-based method that generates smooth exploded-view sequences of 3D objects, enabling part-level decomposition, control, and reassembly.

  2. DepR: Depth Guided Single-view Scene Reconstruction with Instance-level Diffusion

    cs.CV 2025-07 conditional novelty 6.0 of 10

    A single color photo becomes a 3D room scene by generating each object with a depth-conditioned diffusion model, then optimizing object poses against estimated depth.

  3. PartCrafter: Structured 3D Mesh Generation via Compositional Latent Diffusion Transformers

    cs.CV 2025-06 conditional novelty 6.0 of 10

    PartCrafter generates several separable 3D part meshes at once from a single image by fine-tuning a pretrained 3D diffusion transformer with part identity tokens and local-global attention.

  4. DanceTogether! Identity-Preserving Multi-Person Interactive Video Generation

    cs.CV 2025-05 conditional novelty 6.0 of 10

    A diffusion model fuses per-person masks with pose keypoints to generate identity-preserving, two-person interactive videos from a single reference image, outperforming prior single-person-animation pipelines.

  5. Sel3DCraft: Interactive Visual Prompts for User-Friendly Text-to-3D Generation

    cs.GR 2025-08 unverdicted novelty 4.0 of 10

    A visual prompt engineering system for text-to-3D generation uses multi-view MLLM scoring and interactive visualizations to help designers create models faster, with 70.5% time reduction and higher quality ratings (4....

Pith tools