Pith. sign in

REVIEW 5 cited by

3D-Adapter: Geometry-Consistent Multi-View Diffusion for High-Quality 3D Generation

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 2410.18974 v2 pith:JESYQPE2 submitted 2024-10-24 cs.CV cs.AI

Hansheng Chen , Bokui Shen , Yulin Liu , Ruoxi Shi , Linqi Zhou , Connor Z. Lin , Jiayuan Gu , Hao Su
show 2 more authors
Gordon Wetzstein Leonidas Guibas
This is my paper · ORCID
classification cs.CVcs.AI
keywords d-adapterdiffusionmodelsgenerationmulti-viewgeometryhigh-qualityimage
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

Multi-view image diffusion models have significantly advanced open-domain 3D object generation. However, most existing models rely on 2D network architectures that lack inherent 3D biases, resulting in compromised geometric consistency. To address this challenge, we introduce 3D-Adapter, a plug-in module designed to infuse 3D geometry awareness into pretrained image diffusion models. Central to our approach is the idea of 3D feedback augmentation: for each denoising step in the sampling loop, 3D-Adapter decodes intermediate multi-view features into a coherent 3D representation, then re-encodes the rendered RGBD views to augment the pretrained base model through feature addition. We study two variants of 3D-Adapter: a fast feed-forward version based on Gaussian splatting and a versatile training-free version utilizing neural fields and meshes. Our extensive experiments demonstrate that 3D-Adapter not only greatly enhances the geometry quality of text-to-multi-view models such as Instant3D and Zero123++, but also enables high-quality 3D generation using the plain text-to-image Stable Diffusion. Furthermore, we showcase the broad application potential of 3D-Adapter by presenting high quality results in text-to-3D, image-to-3D, text-to-texture, and text-to-avatar tasks.

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. VecSet-Edit: Unleashing Pre-trained LRM for Mesh Editing from Single Image

    cs.CV 2026-02 unverdicted novelty 7.0 of 10

    VecSet-Edit is the first method to perform high-fidelity mesh editing from a single image by analyzing and manipulating spatial token subsets in a pre-trained VecSet LRM.

  2. Pro3D-Editor : A Progressive-Views Perspective for Consistent and Precise 3D Editing

    cs.GR 2025-05 conditional novelty 6.0 of 10

    Pro3D-Editor chooses the most editing-salient view, propagates the edit to other key views with per-view LoRA experts, and refines the 3D scene, improving multi-view consistency.

  3. SplatPainter: Interactive Authoring of 3D Gaussians from 2D Edits via Test-Time Training

    cs.CV 2025-12 conditional novelty 5.0 of 10

    A test-time-trained feedforward model that propagates 2D edits onto 3D Gaussian attributes at interactive speeds.

  4. ERMV: Editing 4D Robotic Multi-view images to enhance embodied agents

    cs.CV 2025-07 conditional novelty 5.0 of 10

    ERMV edits 4D multi-view robot videos from one edited frame plus robot states, and VLA policies trained on the edited data show higher success rates in simulation and real robot tests.

  5. Advancing high-fidelity 3D and Texture Generation with 2.5D latents

    cs.CV 2025-05 conditional novelty 5.0 of 10

    A 2.5D latent combining multiview RGB, normal, and coordinate images, generated by a mixture-of-LoRA fine-tuned Flux model, enables joint 3D geometry and texture generation from text or images.

Pith tools