Share your thoughts, 1 month free Claude Pro on usSee more
WorkDL logo mark

Edit2Perceive: Image Editing Diffusion Models Are Strong Dense Perceivers

About

Recent advances in diffusion transformers have shown remarkable generalization in visual synthesis, yet most dense perception methods still rely on text-to-image (T2I) generators designed for stochastic generation. We revisit this paradigm and show that image editing diffusion models are inherently image-to-image consistent, providing a more suitable foundation for dense perception task. We introduce Edit2Perceive, a unified diffusion framework that adapts editing models for depth, normal, and matting. Built upon the FLUX.1 Kontext architecture, our approach employs full-parameter fine-tuning and a pixel-space consistency loss to enforce structure-preserving refinement across intermediate denoising states. Moreover, our single-step deterministic inference yields up to faster runtime while training on relatively small datasets. Extensive experiments demonstrate comprehensive state-of-the-art results across all three tasks, revealing the strong potential of editing-oriented diffusion transformers for geometry-aware perception.

Yiqing Shi, Yiren Song, Mike Zheng Shou• 2025

Related benchmarks

TaskDatasetResultRank
Surface Normal EstimationiBIMS-1
MAE15.1
67
Monocular Depth EstimationNYU Depth Eigen v2 (test)
A.Rel0.044
57
Monocular Depth EstimationScanNet (val)
AbsRel4.9
15
Surface Normal EstimationNYU (DSINE)
Mean Angular Error15.7
9
Surface Normal EstimationScanNet DSINE
Mean Angular Error14.1
9
Monocular Depth EstimationKITTI Garg crop
AbsRel0.079
8
Showing 6 of 6 rows

Other info

Follow for update