Pith. sign in

REVIEW 5 cited by

Consistent123: Improve Consistency for One Image to 3D Object Synthesis

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 2310.08092 v1 pith:2QY3Q653 submitted 2023-10-12 cs.CV

Consistent123: Improve Consistency for One Image to 3D Object Synthesis

classification cs.CV
keywords viewsconsistencyconsistent123viewnovelattentiondownstreamgeneration
verification ladder T0 review T1 audit T2 compute T3 formal T4 reserved
0 comments
read the original abstract

Large image diffusion models enable novel view synthesis with high quality and excellent zero-shot capability. However, such models based on image-to-image translation have no guarantee of view consistency, limiting the performance for downstream tasks like 3D reconstruction and image-to-3D generation. To empower consistency, we propose Consistent123 to synthesize novel views simultaneously by incorporating additional cross-view attention layers and the shared self-attention mechanism. The proposed attention mechanism improves the interaction across all synthesized views, as well as the alignment between the condition view and novel views. In the sampling stage, such architecture supports simultaneously generating an arbitrary number of views while training at a fixed length. We also introduce a progressive classifier-free guidance strategy to achieve the trade-off between texture and geometry for synthesized object views. Qualitative and quantitative experiments show that Consistent123 outperforms baselines in view consistency by a large margin. Furthermore, we demonstrate a significant improvement of Consistent123 on varying downstream tasks, showing its great potential in the 3D generation field. The project page is available at consistent-123.github.io.

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.

Forward citations

Cited by 5 Pith papers

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

  1. QuadLink: Autoregressive Quad-Dominant Mesh Generation via Point-Relation Learning

    cs.GR 2026-05 unverdicted novelty 7.0

    QuadLink generates anisotropic quad-dominant meshes from point clouds via anchor prediction, centroid-conditioned linking, and quad-first assembly, supporting hybrid n-gon topology.

  2. $\phi$-Scene: Physically Grounded Image-to-3D Scene Reconstruction

    cs.CV 2026-06 unverdicted novelty 6.0

    φ-Scene performs image-to-3D scene reconstruction via topology-driven physical assembly that resolves penetrations with SDF optimization and settles objects with rigid-body simulation.

  3. QuadLink: Autoregressive Quad-Dominant Mesh Generation via Point-Relation Learning

    cs.GR 2026-05 unverdicted novelty 6.0

    QuadLink generates anisotropic quad-dominant meshes from point clouds via a hybrid centroid-conditioned vertex linking model and a Tri-to-Quad data conversion operator.

  4. QuadLink: Autoregressive Quad-Dominant Mesh Generation via Point-Relation Learning

    cs.GR 2026-05 unverdicted novelty 4.0

    QuadLink generates anisotropic quad-dominant meshes from point clouds via autoregressive anchor prediction and centroid-conditioned linking, with a Tri-to-Quad data converter and quad-first assembly.

  5. Hunyuan3D 2.1: From Images to High-Fidelity 3D Assets with Production-Ready PBR Material

    cs.CV 2025-06 unverdicted novelty 3.0

    Hunyuan3D 2.1 is a two-part system with DiT for shape generation and Paint for texture synthesis that produces high-fidelity 3D assets with PBR materials.