Pith. sign in

REVIEW 12 cited by

MV-Adapter: Multi-view Consistent Image Generation Made Easy

Not yet reviewed by Pith; the record is open.

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 2412.03632 v1 pith:MA3736K3 submitted 2024-12-04 cs.CV

classification cs.CV
keywords generationimagemodelsmulti-viewmv-adapteradapterknowledgepre-trained
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

Existing multi-view image generation methods often make invasive modifications to pre-trained text-to-image (T2I) models and require full fine-tuning, leading to (1) high computational costs, especially with large base models and high-resolution images, and (2) degradation in image quality due to optimization difficulties and scarce high-quality 3D data. In this paper, we propose the first adapter-based solution for multi-view image generation, and introduce MV-Adapter, a versatile plug-and-play adapter that enhances T2I models and their derivatives without altering the original network structure or feature space. By updating fewer parameters, MV-Adapter enables efficient training and preserves the prior knowledge embedded in pre-trained models, mitigating overfitting risks. To efficiently model the 3D geometric knowledge within the adapter, we introduce innovative designs that include duplicated self-attention layers and parallel attention architecture, enabling the adapter to inherit the powerful priors of the pre-trained models to model the novel 3D knowledge. Moreover, we present a unified condition encoder that seamlessly integrates camera parameters and geometric information, facilitating applications such as text- and image-based 3D generation and texturing. MV-Adapter achieves multi-view generation at 768 resolution on Stable Diffusion XL (SDXL), and demonstrates adaptability and versatility. It can also be extended to arbitrary view generation, enabling broader applications. We demonstrate that MV-Adapter sets a new quality standard for multi-view image generation, and opens up new possibilities due to its efficiency, adaptability and versatility.

Discussion (0). Continue with ORCID to comment.

Forward citations

Cited by 12 Pith papers

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

  1. VoxHammer: Training-Free Precise and Coherent 3D Editing in Native 3D Space

    cs.CV 2025-08 conditional novelty 7.0 of 10

    A training-free 3D editing method that inverts a source asset into TRELLIS latent space and replaces latents plus attention K/V tokens in unedited regions during re-denosing.

  2. MV-RAG: Retrieval Augmented Multiview Diffusion

    cs.CV 2025-08 conditional novelty 7.0 of 10

    A retrieval-augmented multiview diffusion model conditions on web images to generate 3D-consistent views of rare concepts, trained with a hybrid 3D/2D objective and evaluated on a new OOD benchmark.

  3. MVGBench: Comprehensive Benchmark for Multi-view Generation Models

    cs.GR 2025-06 conditional novelty 7.0 of 10

    MVGBench evaluates multi-view generators through self-consistency of 3D reconstructions and uses this protocol to rank 12 models and build a better one.

  4. EditFlow3D: Automated Local Editing of 3D Assets with Trajectory Preservation

    cs.CV 2026-08 conditional novelty 6.0 of 10

    Mask-guided differential flow with a soft preservation loss enables training-free local 3D editing that keeps unedited regions close to the source asset.

  5. PixGS: Pixel-Space Diffusion for Direct 3D Gaussian Splat Generation

    cs.CV 2026-07 unverdicted novelty 6.0 of 10

    PixGS is a single-stage pixel-space diffusion model that directly produces high-quality 3D Gaussian Splats from text or images in ~1s, outperforming multi-stage latent methods on standard benchmarks.

  6. TInR: Exploring Tool-Internalized Reasoning in Large Language Models

    cs.CL 2026-04 unverdicted novelty 6.0 of 10

    TInR-U internalizes tool knowledge into LLMs via bidirectional alignment, supervised fine-tuning, and reinforcement learning, outperforming standard tool-integrated reasoning in both in-domain and out-of-domain evaluations.

  7. ViewMask-1-to-3: Multi-View Consistent Image Generation via Multimodal Discrete Diffusion Models

    cs.CV 2025-12 conditional novelty 6.0 of 10

    A masked discrete-diffusion transformer generates multiple consistent object views from a single image or text, reporting the best average PSNR/SSIM/LPIPS on GSO and 3D-FUTURE.

  8. SeqTex: Generate Mesh Textures in Video Sequence

    cs.CV 2025-07 conditional novelty 6.0 of 10

    SeqTex adapts a pretrained video diffusion model to directly generate complete UV texture maps by jointly predicting four multi-view images and the UV map as a five-frame sequence.

  9. 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.

  10. Pippo: High-Resolution Multi-View Humans from a Single Image

    cs.CV 2025-02 conditional novelty 6.0 of 10

    A single-image multi-view diffusion transformer generates 1K-resolution turnaround views of humans, with attention biasing for many views and a new reprojection-error metric.

  11. ObjFiller3D: Scaling 3D Object Inpainting to Dense Multi-View Consistency

    cs.CV 2025-08 unverdicted novelty 5.0 of 10

    ObjFiller3D jointly optimizes a dense 360-degree ring of views to inpaint 3D objects with cross-view-consistent textures, reporting higher PSNR and LPIPS than per-view baselines at much lower runtime.

  12. Follow-Your-Instruction: A Comprehensive MLLM Agent for World Data Synthesis

    cs.CV 2025-08 conditional novelty 5.0 of 10

    An MLLM-driven pipeline that composes 3D scenes from assets, optimizes them with multi-view VLM feedback, and renders videos, yielding synthetic data that modestly improves several 2D, 3D, and 4D generative baselines.

Pith tools