Pith. sign in

REVIEW 5 cited by

Drivable 3D Gaussian Avatars

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 2311.08581 v2 pith:J4T2SD5M submitted 2023-11-14 cs.CV

Wojciech Zielonka , Timur Bagautdinov , Shunsuke Saito , Michael Zollhöfer , Justus Thies , Javier Romero This is my paper
classification cs.CV
keywords gaussianprimitivestetrahedronavatarsbodycagesdeformationdrivable
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

We present Drivable 3D Gaussian Avatars (D3GA), a multi-layered 3D controllable model for human bodies that utilizes 3D Gaussian primitives embedded into tetrahedral cages. The advantage of using cages compared to commonly employed linear blend skinning (LBS) is that primitives like 3D Gaussians are naturally re-oriented and their kernels are stretched via the deformation gradients of the encapsulating tetrahedron. Additional offsets are modeled for the tetrahedron vertices, effectively decoupling the low-dimensional driving poses from the extensive set of primitives to be rendered. This separation is achieved through the localized influence of each tetrahedron on 3D Gaussians, resulting in improved optimization. Using the cage-based deformation model, we introduce a compositional pipeline that decomposes an avatar into layers, such as garments, hands, or faces, improving the modeling of phenomena like garment sliding. These parts can be conditioned on different driving signals, such as keypoints for facial expressions or joint-angle vectors for garments and the body. Our experiments on two multi-view datasets with varied body shapes, clothes, and motions show higher-quality results. They surpass PSNR and SSIM metrics of other SOTA methods using the same data while offering greater flexibility and compactness.

Discussion (0). Sign in to comment.

Forward citations

Cited by 5 Pith papers

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

  1. Instant Expressive Gaussian Head Avatars at Over 100 FPS

    cs.CV 2025-12 conditional novelty 7.0 of 10

    A single-photo avatar encoder with per-Gaussian feature-space deformation animates faces at 107 FPS with expression quality competitive with diffusion models.

  2. Self-Learning Expression Deformations for Data-Efficient Gaussian Avatars

    cs.CV 2026-06 unverdicted novelty 6.0 of 10

    SAGE self-learns Gaussian expression deformations via joint surfel-SDF optimization and self-supervised consistency, enabling comparable avatar quality from single frames, monocular rotations, or one-shot inputs.

  3. DevilSight: Augmenting Monocular Human Avatar Reconstruction through a Virtual Perspective

    cs.CV 2025-08 reject novelty 5.0 of 10

    A monocular human avatar reconstruction method generates pseudo back-view videos with a fine-tuned diffusion model and uses them as extra training data for a 3D Gaussian avatar.

  4. LUNA: Learning Universal 3D Human Animation Beyond Skinning

    cs.CV 2026-06 unverdicted novelty 4.0 of 10

    LUNA is an LBS-free neural animation model that maps 2D controls to 3D Gaussian deformations via a transformer motion regressor and hybrid supervision for realistic motion and zero-shot generalization.

  5. SAT: Supervisor Regularization and Animation Augmentation for Two-process Monocular Texture 3D Human Reconstruction

    cs.CV 2025-08 conditional novelty 4.0 of 10

    A two-stage Gaussian-splatting framework with supervisor feature regularization and online animation augmentation improves monocular textured 3D human reconstruction on CustomHuman and THuman3.0.

Pith tools