Papers › A Tale of Two Features: Stable Diffusion Complements DINO for Zero-Shot Semantic Correspondence

A Tale of Two Features: Stable Diffusion Complements DINO for Zero-Shot Semantic Correspondence

24 May 2023NeurIPS 2023 11arXiv:2305.15347archive 2025-07-28

Junyi Zhang, Charles Herrmann, Junhwa Hur, Luisa Polania Cabrera, Varun Jampani, Deqing Sun, Ming-Hsuan Yang

Text-to-image diffusion models have made significant advances in generating and editing high-quality images. As a result, numerous approaches have explored the ability of diffusion model features to understand and process single images for downstream tasks, e.g., classification, semantic segmentation, and stylization. However, significantly less is known about what these features reveal across multiple, different images and objects. In this work, we exploit Stable Diffusion (SD) features for semantic and dense correspondence and discover that with simple post-processing, SD features can perform quantitatively similar to SOTA representations. Interestingly, the qualitative analysis reveals that SD features have very different properties compared to existing representation learning features, such as the recently released DINOv2: while DINOv2 provides sparse but accurate matches, SD features provide high-quality spatial information but sometimes inaccurate semantic matches. We demonstrate that a simple fusion of these two features works surprisingly well, and a zero-shot evaluation using nearest neighbors on these fused features provides a significant performance gain over state-of-the-art methods on benchmark datasets, e.g., SPair-71k, PF-Pascal, and TSS. We also show that these correspondences can enable interesting applications such as instance swapping in two images.

PaperPDFConference PDFCode

In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

Code

Junyi42/sd-dino officialmentioned on GitHubpytorch report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

Dense Pixel Correspondence EstimationRepresentation LearningSemantic SegmentationSemantic correspondence

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Dense Pixel Correspondence Estimation TSS SD+DINO (Zero-shot) Average PCK@0.05 79.7 #1 of 1 Archive leaderboard report
Semantic correspondence PF-PASCAL SD+DINO (Supervised) PCK 93.6 #5 of 15 Archive leaderboard report
Semantic correspondence SPair-71k SD+DINO (Supervised) PCK 74.6 #4 of 22 Archive leaderboard report
Semantic correspondence SPair-71k SD+DINO (Zero-shot) PCK 64.0 #9 of 22 Archive leaderboard report

Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.

Methods

Diffusion

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections