AI Paper Atlas

Research map / Image generation / Text-to-image diffusion

UniPercept: A Unified Diffusion Model for Generalizable Visual Perception

Zuyan Zhao, Zhenliang He, Meina Kan, Shiguang Shan, Xilin Chen

CVPR 2026 · Image generation › Text-to-image diffusion · approach: Text-driven synthesis and semantic guidance

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
train foundation on all 7 base tasks instead of depth only (ablation)UniPercept · DepthAbsRel: 8.4 -> 7.3Improved
train foundation on all 7 base tasks instead of normal only (ablation)UniPercept · Normalmean angular error: 18.5 -> 17.4Improved
add more base tasks (depth only to all 7) (ablation)foundation model · DISmax F-measure: 0.746 -> 0.752Improved
add more base tasks (depth only to all 7) (ablation)foundation model · BSDS500 edgeODS: 0.766 -> 0.773Improved
use foundation-adapter model instead of Sana baseline for DIS adaptation (ablation)UniPercept · DIStraining steps to converge: over 30,000 -> 1000 stepsImproved
widen adapter bottleneck (ratio 128 to 16) (ablation)adapter · metallicityPSNR and SSIM: not given numericallyImproved
fine-tune with 1K samples instead of full data (ablation)UniPercept adapter · BSDS500 edgeODS: 0.806 -> 0.810No clear effect
fine-tune with 1K samples instead of full data (ablation)UniPercept adapter · DIS5Kmax F-measure: .764 -> .758No clear effect
use UniPercept instead of specialist BiRefNetDIS adapter · DIS5Kmax F-measure: .896 -> .764Hurt

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy