Sculpt4D: Generating 4D Shapes via Sparse-Attention Diffusion Transformers

• URL: http://arxiv.org/abs/2604.21592v1
• Date: Thu, 23 Apr 2026 12:18:55 GMT
• Title: Sculpt4D: Generating 4D Shapes via Sparse-Attention Diffusion Transformers
• Abstract summary: Sculpt4D is a native 4D generative framework that seamlessly integrates efficient temporal modeling into a pretrained 3D Transformer.<n>We show that Sculpt4D establishes a new state-of-the-art in temporally coherent 4D synthesis and charts a path toward efficient and scalable 4D generation.
• Score: 70.55535980817577
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Recent breakthroughs in 3D generative modeling have yielded remarkable progress in static shape synthesis, yet high-fidelity dynamic 4D generation remains elusive, hindered by temporal artifacts and prohibitive computational demand. We present Sculpt4D, a native 4D generative framework that seamlessly integrates efficient temporal modeling into a pretrained 3D Diffusion Transformer (Hunyuan3D 2.1), thereby mitigating the scarcity of 4D training data. At its core lies a Block Sparse Attention mechanism that preserves object identity by anchoring to the initial frame while capturing rich motion dynamics via a time-decaying sparse mask. This design faithfully models complex spatiotemporal dependencies with high fidelity, while sidestepping the quadratic overhead of full attention and reducing network total computation by 56%. Consequently, Sculpt4D establishes a new state-of-the-art in temporally coherent 4D synthesis and charts a path toward efficient and scalable 4D generation.

Related papers

• Orthogonal Spatial-temporal Distributional Transfer for 4D Generation [58.30004328671699]
  We propose a framework that transfers rich spatial priors from existing 3D diffusion models and temporal priors from video diffusion models to enhance 4D synthesis.<n>We develop a spatial-temporal-disentangled 4D (STD-4D) Diffusion model, which synthesizes 4D-aware videos through disentangled spatial and temporal latents.<n> Experiments demonstrate that our method significantly outperforms existing approaches, achieving superior spatial-temporal consistency and higher-quality 4D synthesis.
  arXiv  Detail & Related papers  (2026-03-05T11:52:21Z)
• Motion 3-to-4: 3D Motion Reconstruction for 4D Synthesis [53.48281548500864]
  Motion 3-to-4 is a feed-forward framework for synthesising high-quality 4D dynamic objects from a single monocular video.<n>Our model learns a compact motion latent representation and predicts per-frame trajectories to recover complete robustness, temporally coherent geometry.
  arXiv  Detail & Related papers  (2026-01-20T18:59:48Z)
• SS4D: Native 4D Generative Model via Structured Spacetime Latents [50.29500511908054]
  We present SS4D, a native 4D generative model that synthesizes dynamic 3D objects directly from monocular video.<n>We train a generator directly on 4D data, achieving high fidelity, temporal coherence, and structural consistency.
  arXiv  Detail & Related papers  (2025-12-16T10:45:06Z)
• TriDiff-4D: Fast 4D Generation through Diffusion-based Triplane Re-posing [30.542634775083112]
  TriDiff-4D is a novel 4D generative pipeline that employs diffusion-based triplane re-posing to produce high-quality, temporally coherent 4D avatars.<n>By explicitly learning 3D structure and motion priors from large-scale 3D and motion datasets, TriDiff-4D enables skeleton-driven 4D generation that excels in temporal consistency, motion accuracy, computational efficiency, and visual fidelity.
  arXiv  Detail & Related papers  (2025-11-20T18:59:03Z)
• ShapeGen4D: Towards High Quality 4D Shape Generation from Videos [85.45517487721257]
  We introduce a native video-to-4D shape generation framework that synthesizes a single dynamic 3D representation end-to-end from the video.<n>Our method accurately captures non-rigid motion, volume changes, and even topological transitions without per-frame optimization.
  arXiv  Detail & Related papers  (2025-10-07T17:58:11Z)
• Diffusion4D: Fast Spatial-temporal Consistent 4D Generation via Video Diffusion Models [116.31344506738816]
  We present a novel framework, textbfDiffusion4D, for efficient and scalable 4D content generation. We develop a 4D-aware video diffusion model capable of synthesizing orbital views of dynamic 3D assets. Our method surpasses prior state-of-the-art techniques in terms of generation efficiency and 4D geometry consistency.
  arXiv  Detail & Related papers  (2024-05-26T17:47:34Z)
• Consistent4D: Consistent 360{\deg} Dynamic Object Generation from Monocular Video [15.621374353364468]
  Consistent4D is a novel approach for generating 4D dynamic objects from uncalibrated monocular videos. We cast the 360-degree dynamic object reconstruction as a 4D generation problem, eliminating the need for tedious multi-view data collection and camera calibration.
  arXiv  Detail & Related papers  (2023-11-06T03:26:43Z)

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.