Pith. sign in

REVIEW 7 cited by

Emergent Correspondence from Image Diffusion

Not yet reviewed by Pith; the record is open.

Re-run · record.json Download PDF Read on arXiv ↗

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2306.03881 v2 pith:JSA5DZ6B submitted 2023-06-06 cs.CV

Luming Tang , Menglin Jia , Qianqian Wang , Cheng Perng Phoo , Bharath Hariharan This is my paper · ORCID
classification cs.CV
keywords diffusioncorrespondencecorrespondencesdiftfeaturesimageableimages
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

Finding correspondences between images is a fundamental problem in computer vision. In this paper, we show that correspondence emerges in image diffusion models without any explicit supervision. We propose a simple strategy to extract this implicit knowledge out of diffusion networks as image features, namely DIffusion FeaTures (DIFT), and use them to establish correspondences between real images. Without any additional fine-tuning or supervision on the task-specific data or annotations, DIFT is able to outperform both weakly-supervised methods and competitive off-the-shelf features in identifying semantic, geometric, and temporal correspondences. Particularly for semantic correspondence, DIFT from Stable Diffusion is able to outperform DINO and OpenCLIP by 19 and 14 accuracy points respectively on the challenging SPair-71k benchmark. It even outperforms the state-of-the-art supervised methods on 9 out of 18 categories while remaining on par for the overall performance. Project page: https://diffusionfeatures.github.io

Discussion (0). Continue with ORCID to comment.

Forward citations

Cited by 7 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score. Full citation record

  1. MOSAIC: Multi-Subject Personalized Generation via Correspondence-Aware Alignment and Disentanglement

    cs.CV 2025-09 conditional novelty 7.0 of 10

    MOSAIC improves multi-subject personalized image generation by supervising attention maps with semantic point correspondences and a disentanglement loss, and introduces the SemAlign-MS dataset for training.

  2. Feel the Force: Contact-Driven Learning from Humans

    cs.RO 2025-06 conditional novelty 7.0 of 10

    FeelTheForce trains a robot policy on human tactile demonstrations, predicting desired contact forces and using a PD controller to track them on the robot gripper, achieving 77% success across five force-sensitive tasks.

  3. Hallo4D: Multi-Modal Hallucination Mitigation for Consistent Spatio-Temporal Generation

    cs.CV 2026-07 conditional novelty 6.0 of 10

    Hallo4D uses vision-language models to detect and correct spatial and temporal mistakes in AI-generated 3D and 4D content, improving consistency without retraining the base generators.

  4. Hierarchical Concept-to-Appearance Guidance for Multi-Subject Image Generation

    cs.CV 2026-02 conditional novelty 6.0 of 10

    A diffusion-transformer framework with VLM-grounded masked attention and VAE dropout improves identity and prompt fidelity for multi-subject image generation.

  5. EgoZero: Robot Learning from Smart Glasses

    cs.RO 2025-05 conditional novelty 6.0 of 10

    Robot policies trained only on egocentric human videos from smart glasses transfer zero-shot to a Franka gripper, with 70% success across 7 manipulation tasks.

  6. A Few Words Go a Long Way: Language Guided Robot Policy Synthesis

    cs.RO 2026-07 conditional novelty 5.0 of 10

    Interactive LLM program synthesis plus a persistent skill library from natural-language corrections outperforms zero-shot VLAs and one-shot code policies on complex real-robot manipulation.

  7. StorySync: Training-Free Subject Consistency in Text-to-Image Generation via Region Harmonization

    cs.CV 2025-07 unverdicted novelty 5.0 of 10

    A training-free inference-time pipeline uses masked cross-image attention sharing and region harmonization to keep subjects consistent across generated story images.

Pith tools