Pith. sign in

REVIEW 2 cited by

SIGMAN:Scaling 3D Human Gaussian Generation with Millions of Assets

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 2504.06982 v1 pith:AORPMTNW submitted 2025-04-09 cs.CV

classification cs.CV
keywords humanassetsgenerationlarge-scalemulti-viewtrainingdigitizationexisting
verification ladder T0 review T1 audit T2 compute T3 formal

Signed reviews

No signed human review yet.

0 comments
abstract

3D human digitization has long been a highly pursued yet challenging task. Existing methods aim to generate high-quality 3D digital humans from single or multiple views, but remain primarily constrained by current paradigms and the scarcity of 3D human assets. Specifically, recent approaches fall into several paradigms: optimization-based and feed-forward (both single-view regression and multi-view generation with reconstruction). However, they are limited by slow speed, low quality, cascade reasoning, and ambiguity in mapping low-dimensional planes to high-dimensional space due to occlusion and invisibility, respectively. Furthermore, existing 3D human assets remain small-scale, insufficient for large-scale training. To address these challenges, we propose a latent space generation paradigm for 3D human digitization, which involves compressing multi-view images into Gaussians via a UV-structured VAE, along with DiT-based conditional generation, we transform the ill-posed low-to-high-dimensional mapping problem into a learnable distribution shift, which also supports end-to-end inference. In addition, we employ the multi-view optimization approach combined with synthetic data to construct the HGS-1M dataset, which contains $1$ million 3D Gaussian assets to support the large-scale training. Experimental results demonstrate that our paradigm, powered by large-scale training, produces high-quality 3D human Gaussians with intricate textures, facial details, and loose clothing deformation.

Discussion (0). Continue with ORCID to comment.

Forward citations

Cited by 2 Pith papers

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

  1. Go to Zero: Towards Zero-shot Motion Generation with Million-scale Data

    cs.CV 2025-07 conditional novelty 6.0 of 10

    A 7B text-to-motion model trained on the new 2M-clip MotionMillion dataset is reported to generalize zero-shot to complex, out-of-domain prompts.

  2. GAS: Generative Avatar Synthesis from a Single Image

    cs.CV 2025-02 conditional novelty 6.0 of 10

    GAS generates view-consistent, temporally coherent avatars from a single image by feeding NeRF renderings of the target view plus SMPL normal maps into a video diffusion model.

Pith tools