CORTEXA
← Browse
arxivcs.CV2026-07-01

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

Jaeah Lee, Hyunjin Kim, Jaewoong Cho, Gihyun Kwon

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.

View free PDFSource page

Related papers

arxivcs.CV2026-07-03

FairFlow: Demystifying and Mitigating Stereotype Bias in Text-to-Image Diffusion Transformers

Chen Chen, Yuanmin Huang, Zhenfei Zhang, Mi Zhang, Xiaohan Zhang, Yun Xiong, et al.

Multimodal diffusion transformers (MM-DiTs) have emerged as the prevalent backbone for modern text-to-image generation systems. However, they exhibit critical alignment vulnerabilities, systematically manifesting severe stereotype biases even under benign prompts. This poses a si…

View free PDFSource page
arxivcs.CV2026-06-26

PixelU: A U-Shaped Transformer for Efficient End-to-End Pixel Diffusion

Zipeng Guo, Lichen Ma, Yu He, Xiaolong Fu, Jingling Fu, Junshi Huang, et al.

End-to-end pixel-space diffusion models bypass the lossy compression of Latent Diffusion Models (LDMs) but struggle to jointly model low-frequency semantics and high-frequency signals in high-dimensional space. Existing works heavily rely on complex pixel decoders to alleviate th…

View free PDFSource page
arxivcs.CVcs.AIcs.LG2026-07-02

OrbitQuant: Data-Agnostic Quantization for Image and Video Diffusion Transformers

Donghyun Lee, Jitesh Chavan, Duy Nguyen, Sam Huang, Liming Jiang, Priyadarshini Panda, et al.

Diffusion transformers (DiTs) achieve state-of-the-art image and video generation, but their multi-step sampling and growing parameter count make inference expensive. Post-training quantization (PTQ) is the natural remedy, yet DiT activations shift across timesteps, prompts, and…

View free PDFSource page
arxivcs.CV2026-06-29

Nemotron-Labs-Diffusion-Image: Advancing Masked Discrete Diffusion for High-Resolution Image Synthesis

Shufan Li, Greg Heinrich, Hanrong Ye, Yonggan Fu, Aditya Grover, Jan Kautz, et al.

We propose Nemotron-Labs-Diffusion-Image, a state-of-the-art masked discrete diffusion model (MDM) for high-resolution text-to-image synthesis. Compared with prior work on masked image generation, Nemotron-Labs-Diffusion-Image addresses two key challenges. First, unlike continuou…

View free PDFSource page
arxivcs.LGcs.CV2026-07-23

KroQuant: Kronecker-Structured Block Transforms for Efficient Post-Training Quantization of Diffusion Transformers

Yann Bouquet, Alireza Khodamoradi, Kristof Denolf, Mathieu Salzmann

Post-training quantization (PTQ) of diffusion transformers (DiTs) to W4A4 severely degrades output quality, because activations entering each linear layer contain outliers that 4-bit formats cannot represent. The standard fix applies an invertible linear transform to the activati…

View free PDFSource page
arxiveess.IVcs.CV2026-07-21

Wavefront Parallelization for Efficient Learned Image Compression

Shimon Murai, Fangzheng Lin, Kasidis Arunruangsirilert, Jiro Katto

Autoregressive context models are foundational for learned image compression,but they suffer from slow serial inference. Existing acceleration methods such as checkerboard context require architectural changes and retraining, thus are inapplicable to pre-trained models. We propos…

View free PDFSource page