CORTEXA
← Browse
arxivcs.CV2026-07-20

DuSPiT: Dual-Branch Sub-Patch Pixel Diffusion Transformer

Yunpeng Bai, Yossi Gandelsman, Michaël Gharbi

Diffusion Transformers achieve strong image generation performance, but most operate in compressed latent spaces. Pixel-space diffusion avoids this information loss, yet existing approaches map each raw image patch to a single token, forcing one representation to handle both global communication and fine-grained details. We address this issue by proposing a new architecture, \textbf{DuSPiT}, a \textbf{Du}al-branch \textbf{S}ub\textbf{P}atch \textbf{Pi}xel \textbf{T}ransformer. This model separates global structural reasoning from local appearance modeling. DuSPiT uses a compact base branch for efficient global reasoning and a parallel, high-capacity pixel branch, organized into subpatch groups, to preserve detailed appearance, with the two branches interacting through cross-attention. Our results show that DuSPiT generates images with richer details and stronger fine-grained structures, while also achieving a better quality--efficiency trade-off than prior pixel-space diffusion transformers.

View free PDFSource page

Related papers

arxivcs.CV2026-06-29

GeoEdit: Geometry-Aware Object Editing via Dual-Branch Denoising

Yi He, Jiangming Wang, Xinyu Wang, Mark Fong, Songchun Zhang, Yuxuan Xue, et al.

Precisely manipulating objects in a single photograph (translation, rotation, scaling) while obeying 3D physical constraints remains unsolved for diffusion-based editors. Current 2D methods lack spatial awareness and produce perspective violations. Forcing structural proxies into…

View free PDFSource page
arxivcs.CVcs.AI2026-07-31

DualDiT: A Conditional Dual-Output Diffusion Transformer for Joint OCT Image and Segmentation Mask Generation

Fernando García-Torres, Rocío del Amor, Sandra Morales, Álvaro Barroso, Peter Heiduschka, Björn Kemper, et al.

Background and Objective: Generating realistic medical images with anatomically accurate segmentation masks helps address the shortage of annotated data in medical imaging, particularly in optical coherence tomography (OCT) of mouse eyes, where manual retinal layer delineation is…

View free PDFSource page
arxivcs.CV2026-07-17

Multi-Modal Semantic Segmentation of Electrolyzer Components for Sustainable Hydrogen Technologies: A Dual-Branch Deep Learning Approach

Wasimul Karim, Nur Mohammad Fahad, Abdul Hasib Siddique, Md Rafiqul Islam, Hooman Mehdizadeh-Rad, Asif Karim, et al.

Accurate segmentation of electrolyzer materials is essential for automated disassembly, sustainable recycling, and circular manufacturing in hydrogen technologies. However, this task is challenging due to strong visual similarity between materials, spectral overlap, irregular sha…

View free PDFSource page
arxivcs.CV2026-07-23

Webly Supervised Multi-Label Recognition: Evaluation Benchmark and Dual-Branch Multi-Label Contrastive Learning

Zhihua Xu, Zhijing Yang, Yufeng Yang, Tianshui Chen

Training deep learning models with freely available web images can reduce their dependence on costly manual annotations. Although webly supervised learning has been widely studied for single-label recognition, its multi-label counterpart remains underexplored, partly due to the l…

View free PDFSource page