Pith. sign in

REVIEW 4 cited by

DreamCube: 3D Panorama Generation via Multi-plane Synchronization

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 2506.17206 v1 pith:SD3A37LM submitted 2025-06-20 cs.GR cs.CVcs.LG

Yukun Huang , Yanning Zhou , Jianan Wang , Kaiyi Huang , Xihui Liu This is my paper
classification cs.GRcs.CVcs.LG
keywords generationfoundationmulti-planepanoramapanoramicdemonstratediversedreamcube
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

3D panorama synthesis is a promising yet challenging task that demands high-quality and diverse visual appearance and geometry of the generated omnidirectional content. Existing methods leverage rich image priors from pre-trained 2D foundation models to circumvent the scarcity of 3D panoramic data, but the incompatibility between 3D panoramas and 2D single views limits their effectiveness. In this work, we demonstrate that by applying multi-plane synchronization to the operators from 2D foundation models, their capabilities can be seamlessly extended to the omnidirectional domain. Based on this design, we further introduce DreamCube, a multi-plane RGB-D diffusion model for 3D panorama generation, which maximizes the reuse of 2D foundation model priors to achieve diverse appearances and accurate geometry while maintaining multi-view consistency. Extensive experiments demonstrate the effectiveness of our approach in panoramic image generation, panoramic depth estimation, and 3D scene generation.

Discussion (0). Sign in to comment.

Forward citations

Cited by 4 Pith papers

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

  1. Unified Panoramic Geometry Estimation via Multi-View Foundation Models

    cs.CV 2026-05 unverdicted novelty 6.0 of 10

    PaGeR is a framework that lifts perspective 3D foundation models to omnidirectional images through mixed training, enabling unified prediction of scale-invariant depth, metric depth, surface normals, and sky masks fro...

  2. EmoSpace: Immersive Affective Image Generation Guided by Fine-Grained Emotion Prototypes

    cs.CV 2026-02 conditional novelty 6.0 of 10

    EmoSpace generates emotion-controlled images and VR panoramas via a dynamic bank of 1,024 CLIP-space emotion prototypes, reporting higher fine-grained emotional alignment than baseline diffusion models.

  3. OmniX: From Unified Panoramic Generation and Perception to Graphics-Ready 3D Scenes

    cs.CV 2025-10 conditional novelty 6.0 of 10

    OmniX trains separate LoRA adapters on FLUX.1-dev so one framework handles panorama generation, intrinsic perception (depth, normals, albedo, roughness, metallic), and completion, then feeds the maps into PBR-ready 3D scenes.

  4. Gimbal360: Canonicalizing Planar Diffusion for Spherical Panorama Completion

    cs.CV 2026-03 reject novelty 5.0 of 10

    Gimbal360 completes 360° panoramas from unposed perspective images by rigidly auto-leveling inputs and training diffusion with a Siamese shift-equivariance loss to preserve ERP seam continuity.

Pith tools