Semantic correspondence
6개 벤치마크 · 논문 237편 · 이 태스크의 논문 보기 →
Benchmarks
SPair-71k
PF-PASCAL
PF-WILLOW
Caltech-101
AP-10K
CUB-200-2011
Most implemented
OmniVAE: An Audio-Video VAE with Cross-Modal Alignment for Joint Generation
Color2Embed: Fast Exemplar-Based Image Colorization using Color Embeddings
DiscoBox: Weakly Supervised Instance Segmentation and Semantic Correspondence from Box Supervision
PatentMatch: A Dataset for Matching Patent Claims & Prior Art
Neighbourhood Consensus Networks
Vorch-IR: Long-Form Unified Multimodal Identity Replacement Video Generation
Papers
EDITBRIDGE: Towards Faithful and Efficient Ultra-High-Resolution Image Editing
High-resolution image editing is increasingly demanded in professional workflows, yet existing diffusion-based models remain constrained to resolutions below 1K due to quadratic attention complexity and prohibitive memor…
Semantic correspondenceImage EditingRevisiting Classifier-Free Guidance Methods in Latent Diffusion Models
Inference-time quality-enhancement methods are an effective and widely adopted means of improving diffusion models without expensive retraining. We study a family of training-free techniques conceptually rooted in Classi…
Semantic correspondenceVorch-IR: Long-Form Unified Multimodal Identity Replacement Video Generation
Video identity replacement seeks to transfer the identities of one or more subjects while preserving the motion, expressions, and temporal structure of a driving video. Existing methods largely target single-person setti…
Semantic correspondenceVideo GenerationOmniVAE: An Audio-Video VAE with Cross-Modal Alignment for Joint Generation
Recent generative models are moving beyond silent video or standalone audio synthesis toward the joint generation of synchronized audio and video. Despite this progress, jointly generating audio and video with fine-grain…
Semantic correspondenceVideo GenerationOASIS-Map: Object-Level Change Detection in Multi-Session Mapping using Semantic Correspondence Matching
Map representations which are consistent across repeated visits to a real-world semi-static environment are very useful for long-term robotic inspection. In such settings, the scene may evolve while the robot is absent, …
Semantic correspondenceChange DetectionREBASE: Reference-Background Subspace Elimination for Training-Free In-Context Segmentation
Training-free in-context segmentation enables new object categories to be introduced at inference time from a single annotated reference image, eliminating the retraining and memory overhead of class-incremental learning…
class-incremental learningSemantic correspondence