Vitality-Aware Compression for Efficient Image-to-Shape Diffusion Transformers

• URL: http://arxiv.org/abs/2607.00382v1
• Date: Wed, 01 Jul 2026 03:26:41 GMT
• Title: Vitality-Aware Compression for Efficient Image-to-Shape Diffusion Transformers
• Abstract summary: We propose the first compression approach for image-to-shape Diffusion Transformers (DiTs) that substantially reduces model size while preserving geometric fidelity.<n>Our method achieves up to 66% model-size reduction across state-of-the-art image-to-3D models while maintaining synthesis fidelity comparable to full-sized counterparts.
• Score: 27.13288410891471
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: We propose the first compression approach for image-to-shape Diffusion Transformers (DiTs) that substantially reduces model size while preserving geometric fidelity. Despite remarkable progress in 3D shape generation, large DiT-based models remain computationally prohibitive in resource-constrained settings. Furthermore, it is difficult to directly transfer existing diffusion model compression strategies developed for different domains to 3D generation, and prior 3D efficiency approaches focus primarily on inference speed rather than backbone compression. To address this limitation, we build a geometry-aware compression framework tailored to image-to-shape DiTs. Guided by the observation that 3D DiT layers exhibit non-uniform importance for geometry synthesis, we introduce a vitality-guided framework integrating structured pruning, adaptive quantization, and targeted fine-tuning. Our method achieves up to 66% model-size reduction across state-of-the-art image-to-3D models while maintaining synthesis fidelity comparable to full-sized counterparts. This highlights the potential of our framework as a plug-and-play solution for efficient 3D shape generation across diverse models.

Related papers

• Towards Realistic and Consistent Orbital Video Generation via 3D Foundation Priors [61.34273238077091]
  We present a novel method for generating orbital videos from a single image of an object.<n>Our method achieves superior visual quality, shape realism and multi-view consistency compared to state-of-the-art methods.
  arXiv  Detail & Related papers  (2026-04-14T05:35:46Z)
• UniLat3D: Geometry-Appearance Unified Latents for Single-Stage 3D Generation [98.40254523605581]
  UniLat3D is a unified framework that encodes geometry and appearance in a single latent space.<n>Our key contribution is a geometry-appearance Unified VAE, which compresses high-resolution sparse features into a compact latent representation.<n>UniLat3D produces high-quality 3D assets in seconds from a single image.
  arXiv  Detail & Related papers  (2025-09-29T17:21:23Z)
• Enhancing Single Image to 3D Generation using Gaussian Splatting and Hybrid Diffusion Priors [17.544733016978928]
  3D object generation from a single image involves estimating the full 3D geometry and texture of unseen views from an unposed RGB image captured in the wild. Recent advancements in 3D object generation have introduced techniques that reconstruct an object's 3D shape and texture. We propose bridging the gap between 2D and 3D diffusion models to address this limitation.
  arXiv  Detail & Related papers  (2024-10-12T10:14:11Z)
• GeoLRM: Geometry-Aware Large Reconstruction Model for High-Quality 3D Gaussian Generation [65.33726478659304]
  We introduce the Geometry-Aware Large Reconstruction Model (GeoLRM), an approach which can predict high-quality assets with 512k Gaussians and 21 input images in only 11 GB GPU memory. Previous works neglect the inherent sparsity of 3D structure and do not utilize explicit geometric relationships between 3D and 2D images. GeoLRM tackles these issues by incorporating a novel 3D-aware transformer structure that directly processes 3D points and uses deformable cross-attention mechanisms.
  arXiv  Detail & Related papers  (2024-06-21T17:49:31Z)
• Compress3D: a Compressed Latent Space for 3D Generation from a Single Image [27.53099431097921]
  Triplane autoencoder encodes 3D models into a compact triplane latent space to compress both the 3D geometry and texture information. We introduce a 3D-aware cross-attention mechanism, which utilizes low-resolution latent representations to query features from a high-resolution 3D feature volume. Our approach enables the generation of high-quality 3D assets in merely 7 seconds on a single A100 GPU.
  arXiv  Detail & Related papers  (2024-03-20T11:51:04Z)
• CRM: Single Image to 3D Textured Mesh with Convolutional Reconstruction Model [37.75256020559125]
  We present a high-fidelity feed-forward single image-to-3D generative model. We highlight the necessity of integrating geometric priors into network design. Our model delivers a high-fidelity textured mesh from an image in just 10 seconds, without any test-time optimization.
  arXiv  Detail & Related papers  (2024-03-08T04:25:29Z)
• Pushing Auto-regressive Models for 3D Shape Generation at Capacity and Scalability [118.26563926533517]
  Auto-regressive models have achieved impressive results in 2D image generation by modeling joint distributions in grid space. We extend auto-regressive models to 3D domains, and seek a stronger ability of 3D shape generation by improving auto-regressive models at capacity and scalability simultaneously.
  arXiv  Detail & Related papers  (2024-02-19T15:33:09Z)
• Wonder3D: Single Image to 3D using Cross-Domain Diffusion [105.16622018766236]
  Wonder3D is a novel method for efficiently generating high-fidelity textured meshes from single-view images. To holistically improve the quality, consistency, and efficiency of image-to-3D tasks, we propose a cross-domain diffusion model.
  arXiv  Detail & Related papers  (2023-10-23T15:02:23Z)
• Learning Versatile 3D Shape Generation with Improved AR Models [91.87115744375052]
  Auto-regressive (AR) models have achieved impressive results in 2D image generation by modeling joint distributions in the grid space. We propose the Improved Auto-regressive Model (ImAM) for 3D shape generation, which applies discrete representation learning based on a latent vector instead of volumetric grids.
  arXiv  Detail & Related papers  (2023-03-26T12:03:18Z)
• Efficient Geometry-aware 3D Generative Adversarial Networks [50.68436093869381]
  Existing 3D GANs are either compute-intensive or make approximations that are not 3D-consistent. In this work, we improve the computational efficiency and image quality of 3D GANs without overly relying on these approximations. We introduce an expressive hybrid explicit-implicit network architecture that synthesizes not only high-resolution multi-view-consistent images in real time but also produces high-quality 3D geometry.
  arXiv  Detail & Related papers  (2021-12-15T08:01:43Z)

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.