Pith. sign in

REVIEW 7 cited by

Atlas Gaussians Diffusion for 3D Generation

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 2408.13055 v3 pith:K5IILP4G submitted 2024-08-23 cs.CV

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

Using the latent diffusion model has proven effective in developing novel 3D generation techniques. To harness the latent diffusion model, a key challenge is designing a high-fidelity and efficient representation that links the latent space and the 3D space. In this paper, we introduce Atlas Gaussians, a novel representation for feed-forward native 3D generation. Atlas Gaussians represent a shape as the union of local patches, and each patch can decode 3D Gaussians. We parameterize a patch as a sequence of feature vectors and design a learnable function to decode 3D Gaussians from the feature vectors. In this process, we incorporate UV-based sampling, enabling the generation of a sufficiently large, and theoretically infinite, number of 3D Gaussian points. The large amount of 3D Gaussians enables the generation of high-quality details. Moreover, due to local awareness of the representation, the transformer-based decoding procedure operates on a patch level, ensuring efficiency. We train a variational autoencoder to learn the Atlas Gaussians representation, and then apply a latent diffusion model on its latent space for learning 3D Generation. Experiments show that our approach outperforms the prior arts of feed-forward native 3D generation. Project page: https://yanghtr.github.io/projects/atlas_gaussians.

Discussion (0). Sign in to comment.

Forward citations

Cited by 7 Pith papers

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

  1. Structured 3D Latents for Scalable and Versatile 3D Generation

    cs.CV 2024-12 unverdicted novelty 7.0 of 10

    SLAT provides a unified 3D latent representation enabling versatile high-quality generation across multiple output formats from text or image inputs.

  2. Generative 3D Gaussians with Learned Density Control

    cs.GR 2026-05 unverdicted novelty 6.0 of 10

    DeG models 3D Gaussians via learned octree density and uses VecSeq Sobol re-indexing to turn set generation into sequence modeling, claiming SOTA quality in single-image-to-3D.

  3. LSRM: High-Fidelity Object-Centric Reconstruction via Scaled Context Windows

    cs.CV 2026-04 conditional novelty 6.0 of 10

    LSRM scales transformer context windows with native sparse attention and geometric routing to deliver high-fidelity feed-forward 3D reconstruction and inverse rendering that approaches dense optimization quality.

  4. LSRM: High-Fidelity Object-Centric Reconstruction via Scaled Context Windows

    cs.CV 2026-04 conditional novelty 6.0 of 10

    Scaling sparse transformer context to 20× more object tokens yields feed-forward 3D reconstructions with >2.4 dB higher PSNR and LPIPS that matches dense-view optimization.

  5. LSRM: High-Fidelity Object-Centric Reconstruction via Scaled Context Windows

    cs.CV 2026-04 conditional novelty 6.0 of 10

    Scaling transformer context with sparse attention and 3D-aware block routing improves feed-forward 3D reconstruction and inverse rendering, closing much of the quality gap with dense-view optimization.

  6. Native and Compact Structured Latents for 3D Generation

    cs.CV 2025-12 unverdicted novelty 6.0 of 10

    Introduces O-Voxel omni-voxel representation and Sparse Compression VAE for structured native 3D latents, enabling efficient training of large flow-matching models that produce higher-quality geometry and materials th...

  7. Gaussian Variation Field Diffusion for High-fidelity Video-to-4D Synthesis

    cs.CV 2025-07 conditional novelty 6.0 of 10

    A video-to-4D model that encodes mesh animations into compact Gaussian variation latents and diffuses them conditioned on the video and a canonical Gaussian splat.

Pith tools