Pith. sign in

REVIEW 12 cited by

Cycle3D: High-quality and Consistent Image-to-3D Generation via Generation-Reconstruction Cycle

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 2407.19548 v1 pith:VZYOPVGH submitted 2024-07-28 cs.CV

Zhenyu Tang , Junwu Zhang , Xinhua Cheng , Wangbo Yu , Chaoran Feng , Yatian Pang , Bin Lin , Li Yuan This is my paper · ORCID
classification cs.CV
keywords diffusionmodelgenerationmulti-viewreconstructionconsistencycontenthigh-quality
verification ladder T0 review T1 audit T2 compute T3 formal

Signed reviews

No signed human review yet.

0 comments
read the original abstract

Recent 3D large reconstruction models typically employ a two-stage process, including first generate multi-view images by a multi-view diffusion model, and then utilize a feed-forward model to reconstruct images to 3D content.However, multi-view diffusion models often produce low-quality and inconsistent images, adversely affecting the quality of the final 3D reconstruction. To address this issue, we propose a unified 3D generation framework called Cycle3D, which cyclically utilizes a 2D diffusion-based generation module and a feed-forward 3D reconstruction module during the multi-step diffusion process. Concretely, 2D diffusion model is applied for generating high-quality texture, and the reconstruction model guarantees multi-view consistency.Moreover, 2D diffusion model can further control the generated content and inject reference-view information for unseen views, thereby enhancing the diversity and texture consistency of 3D generation during the denoising process. Extensive experiments demonstrate the superior ability of our method to create 3D content with high-quality and consistency compared with state-of-the-art baselines.

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. Hypothesis-and-Refinement Learning of Organic Structures from Multimodal Spectroscopic Data

    physics.chem-ph 2026-07 conditional novelty 6.0 of 10

    A two-stage AI pipeline — spectral hypothesis generation followed by mass-constrained molecular refinement — reconstructs organic structures from multimodal spectra, with 93.8% top-1 accuracy on simulated QM9 data and...

  2. E-4DGS: High-Fidelity Dynamic Reconstruction from the Multi-view Event Cameras

    cs.CV 2025-08 conditional novelty 6.0 of 10

    E-4DGS is a deformable 3D Gaussian Splatting method that reconstructs dynamic scenes directly from multi-view event camera streams, outperforming event-to-image baseline approaches.

  3. OpenS2V-Nexus: A Detailed Benchmark and Million-Scale Dataset for Subject-to-Video Generation

    cs.CV 2025-05 conditional novelty 6.0 of 10

    A benchmark and five-million-clip dataset for evaluating and training subject-to-video generation models, with three new metrics for subject consistency, naturalness, and text alignment.

  4. GS2E: Gaussian Splatting is an Effective Data Generator for Event Stream Generation

    cs.CV 2025-05 conditional novelty 6.0 of 10

    A pipeline that turns sparse multi-view RGB images into a claimed 1,150-scene synthetic event dataset using 3D Gaussian Splatting rendering plus a stochastic event simulator.

  5. EchoVideo: Identity-Preserving Human Video Generation by Multimodal Feature Fusion

    cs.CV 2025-01 conditional novelty 6.0 of 10

    EchoVideo preserves identity in generated human videos by pre-fusing face, image, and text features, then training with stochastic shallow-feature dropout to reduce copy-paste artifacts.

  6. Ingredients: Blending Custom Photos with Video Diffusion Transformers

    cs.CV 2025-01 conditional novelty 6.0 of 10

    Ingredients adds a mask-supervised identity router to a video diffusion transformer, enabling multi-person videos from a few reference photos without per-identity fine-tuning.

  7. Navigating Chemical-Linguistic Sharing Space with Heterogeneous Molecular Encoding

    cs.CE 2024-12 conditional novelty 6.0 of 10

    A multi-view molecular encoder with fragment-based chain-of-thought improves text-to-molecule and molecule-to-text generation, supported by a new one-million-molecule conditional design dataset.

  8. DreamDance: Animating Human Images by Enriching 3D Geometry Cues from 2D Poses

    cs.CV 2024-11 conditional novelty 6.0 of 10

    A two-stage diffusion pipeline that enriches 2D pose guidance with generated depth and normal maps to achieve state-of-the-art human image animation.

  9. Identity-Preserving Text-to-Video Generation by Frequency Decomposition

    cs.CV 2024-11 conditional novelty 6.0 of 10

    ConsisID generates identity-preserving videos by injecting low-frequency facial features into shallow layers and high-frequency identity features into attention blocks of a DiT video model.

  10. Fancy123: One Image to High-Quality 3D Mesh Generation via Plug-and-Play Deformation

    cs.CV 2024-11 conditional novelty 6.0 of 10

    Fancy123 refines single-image-to-3D meshes by deforming multiview images and then the mesh itself, then unprojecting clear image colors onto the surface.

  11. AE-NeRF: Augmenting Event-Based Neural Radiance Fields for Non-ideal Conditions and Larger Scene

    cs.CV 2025-01 conditional novelty 5.0 of 10

    AE-NeRF jointly optimizes camera poses and an event-based NeRF with a proposal network and four event-specific losses, improving novel view synthesis under noisy poses and non-uniform motion.

  12. Hierarchical Banzhaf Interaction for General Video-Language Representation Learning

    cs.CV 2024-12 conditional novelty 4.0 of 10

    HBI V2 models video-text alignment as a cooperative game with Hierarchical Banzhaf Interaction plus single/cross-modal representation fusion, improving retrieval, QA, and captioning benchmarks.

Pith tools