VARPose: Flexible 2D Pose Densification via Visual Autoregressive Modeling for Enhanced 3D Lifting

• URL: http://arxiv.org/abs/2608.02214v1
• Date: Mon, 03 Aug 2026 13:36:24 GMT
• Title: VARPose: Flexible 2D Pose Densification via Visual Autoregressive Modeling for Enhanced 3D Lifting
• Abstract summary: VARPose is proposed to adaptively densify 2D sparse poses, thereby enriching the anatomical information available for 3D lifting models.<n>We introduce a Granularity-agnostic Pose Tokenizer (GPT), which employs a single hybrid codebook and a residual quantization strategy to encode poses of varying densities into a unified, multi-scale discrete representation.<n>We also propose UniSkelar, a unified autoregressive model that treats "joint density" as "scale"
• Score: 9.224176101167693
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Visual AutoRegressive Modeling (VAR) has excelled in natural image generation via next-scale prediction, but its use on topology-structured data like human skeletons is still unexplored. VARPose is proposed to adaptively densify 2D sparse poses, thereby enriching the anatomical information available for 3D lifting models. Our core contributions are twofold. First, we introduce a Granularity-agnostic Pose Tokenizer (GPT), which employs a single hybrid codebook and a residual quantization strategy to encode poses of varying densities into a unified, multi-scale discrete representation. Our results demonstrate the strong generalizability of this representation. By decoupling the representation from the projection, we can successfully decode novel pose granularities using a frozen codebook with a retrained decoder. Second, we propose UniSkelar, a unified autoregressive model that treats "joint density" as "scale". UniSkelar learns to predict the token sequence for the next density level in a coarse-to-fine manner, conditioned on the sparsest pose. VARPose not only outperforms state-of-the-art methods and generalizes to unseen granularities, but also confers tangible performance gains on downstream tasks, such as 3D Pose Estimation and Human Mesh Recovery, through 2D pose densification. Our code and model are available at https://github.com/BRL-SYSU/VARPose.git.

Related papers

• G-Skin: Learning to Bind 3D Gaussians with Generative Visual Priors [51.398600453223274]
  G-Skin is a novel generative skinning framework designed for expressive and high-fidelity animation with 3D Gaussian representation.<n>We introduce a skeleton-controllable image generation model leveraging 2D vision foundation models to distill powerful motion priors into pseudo-guidance.<n>G-Skin also generalizes flexibly to the augmented variants of 3D Gaussian representation designed to mitigate animation-induced rendering artifacts.
  arXiv  Detail & Related papers  (2026-08-03T05:45:23Z)
• S2D: Sparse to Dense Lifting for 3D Reconstruction with Minimal Inputs [53.597239706600455]
  We introduce Sparse to Dense lifting (S2D), a novel pipeline that bridges the two representations and achieves high-quality 3DGS reconstruction with minimal inputs.<n>Experiments show that S2D achieves the best consistency in generating novel view guidance and first-tier sparse view reconstruction quality under different input sparsity.
  arXiv  Detail & Related papers  (2026-03-11T15:37:20Z)
• SPFSplatV2: Efficient Self-Supervised Pose-Free 3D Gaussian Splatting from Sparse Views [18.814209805277503]
  SPFSplatV2, an efficient feed-forward framework for 3D Gaussian splatting from sparse multi-view images, is presented.<n>Method achieves state-of-the-art performance in both in-domain and out-of-domain novel view synthesis.
  arXiv  Detail & Related papers  (2025-09-21T21:37:56Z)
• HiPART: Hierarchical Pose AutoRegressive Transformer for Occluded 3D Human Pose Estimation [61.32714172038278]
  We propose a novel two-stage generative densification method, named Hierarchical Pose AutoRegressive Transformer (HiPART), to generate 2D dense poses from the original sparse 2D pose.<n>Specifically, we first develop a multi-scale skeleton tokenization module to quantize the highly dense 2D pose into hierarchical tokens and propose a Skeleton-aware Alignment to strengthen token connections.<n>With generated hierarchical poses as inputs for 2D-to-3D lifting, the proposed method shows strong robustness in occluded scenarios and achieves state-of-the-art performance on the single-frame-based 3D
  arXiv  Detail & Related papers  (2025-03-30T06:15:36Z)
• Adapting Human Mesh Recovery with Vision-Language Feedback [17.253535686451897]
  We leverage vision-language models to generate interactive body part descriptions.<n>We train a text encoder and a pose VQ-VAE, aligning texts to body poses in a shared latent space.<n>The model can produce poses with accurate 3D perception and image consistency.
  arXiv  Detail & Related papers  (2025-02-06T07:42:00Z)
• GenHMR: Generative Human Mesh Recovery [14.708444067294325]
  GenHMR is a novel generative framework that reformulates monocular HMR as an image-conditioned generative task.<n>Experiments on benchmark datasets demonstrate that GenHMR significantly outperforms state-of-the-art methods.
  arXiv  Detail & Related papers  (2024-12-19T01:45:58Z)
• No Pose, No Problem: Surprisingly Simple 3D Gaussian Splats from Sparse Unposed Images [100.80376573969045]
  NoPoSplat is a feed-forward model capable of reconstructing 3D scenes parameterized by 3D Gaussians from multi-view images. Our model achieves real-time 3D Gaussian reconstruction during inference. This work makes significant advances in pose-free generalizable 3D reconstruction and demonstrates its applicability to real-world scenarios.
  arXiv  Detail & Related papers  (2024-10-31T17:58:22Z)
• GSD: View-Guided Gaussian Splatting Diffusion for 3D Reconstruction [52.04103235260539]
  We present a diffusion model approach based on Gaussian Splatting representation for 3D object reconstruction from a single view. The model learns to generate 3D objects represented by sets of GS ellipsoids. The final reconstructed objects explicitly come with high-quality 3D structure and texture, and can be efficiently rendered in arbitrary views.
  arXiv  Detail & Related papers  (2024-07-05T03:43:08Z)
• GVA: Reconstructing Vivid 3D Gaussian Avatars from Monocular Videos [56.40776739573832]
  We present a novel method that facilitates the creation of vivid 3D Gaussian avatars from monocular video inputs (GVA) Our innovation lies in addressing the intricate challenges of delivering high-fidelity human body reconstructions. We introduce a pose refinement technique to improve hand and foot pose accuracy by aligning normal maps and silhouettes.
  arXiv  Detail & Related papers  (2024-02-26T14:40:15Z)
• Designing BERT for Convolutional Networks: Sparse and Hierarchical Masked Modeling [23.164631160130092]
  We extend the success of BERT-style pre-training, or the masked image modeling, to convolutional networks (convnets) We treat unmasked pixels as sparse voxels of 3D point clouds and use sparse convolution to encode. This is the first use of sparse convolution for 2D masked modeling.
  arXiv  Detail & Related papers  (2023-01-09T18:59:50Z)
• 3D Human Pose Regression using Graph Convolutional Network [68.8204255655161]
  We propose a graph convolutional network named PoseGraphNet for 3D human pose regression from 2D poses. Our model's performance is close to the state-of-the-art, but with much fewer parameters.
  arXiv  Detail & Related papers  (2021-05-21T14:41:31Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.