A 3D-aware framework uses SAM3D geometry and pose estimation plus geodesic filtering to supervise a lightweight adapter on DINO and Stable Diffusion features, improving semantic correspondence with less manual supervision.
Spair-71k: A large-scale benchmark for semantic correspon- dence
9 Pith papers cite this work. Polarity classification is still indexing.
9
Pith papers citing it
citation-role summary
dataset 1
citation-polarity summary
fields
cs.CV 9roles
dataset 1polarities
use dataset 1representative citing papers
Morpheus learns morphable category-level shape priors to produce implicit 3D correspondences in camera space without explicit supervision and releases the HouseCorr3D benchmark with amodal and symmetry annotations.
Zero-ablation overstates register content dependence in DINO ViTs because mean, noise, and cross-image shuffle replacements preserve performance while zeroing does not.
Weighted Reverse Convolution is a spatially adaptive inverse operator for densifying high-level visual descriptors from vision foundation models, using weighted regularization and an FFT closed-form solution to improve dense prediction tasks.
MARCO achieves new state-of-the-art semantic correspondence on SPair-71k, AP-10K and PF-PASCAL by combining coarse-to-fine refinement with self-distillation on DINOv2, delivering larger gains at fine thresholds and on unseen keypoints and categories while using 3x fewer parameters and running 10x更快.
VLMs bypass visual comparison by recovering semantic labels for nameable entities and hallucinate on unnamable ones, as shown by performance gaps and Logit Lens analysis.
Franca introduces nested Matryoshka clustering and positional disentanglement in a transparent SSL pipeline to deliver open-source vision models competitive with closed proprietary systems.
Normalized Matching Transformer enforces unit-norm embeddings at every Transformer layer and trains with InfoNCE plus hyperspherical uniformity loss, reaching new state-of-the-art accuracy on PascalVOC and SPair-71k while converging faster than prior matching networks.
BLINK benchmark shows multimodal LLMs reach only 45-51 percent accuracy on core visual perception tasks where humans achieve 95 percent, indicating these abilities have not emerged.
citing papers explorer
-
BLINK: Multimodal Large Language Models Can See but Not Perceive
BLINK benchmark shows multimodal LLMs reach only 45-51 percent accuracy on core visual perception tasks where humans achieve 95 percent, indicating these abilities have not emerged.