activity
20242026
collaborators

5 papers

cs.CV2026

Naïve PAINE: Lightweight Text-to-Image Generation Improvement with Prompt Evaluation

Joong Ho Kim, Nicholas Thai, Souhardya Saha Dip +2

Text-to-Image (T2I) generation is primarily driven by Diffusion Models (DM) which rely on random Gaussian noise. Thus, like playing the slots at a casino, a DM will produce differe…

cs.CV2026

Triangular Consistency as a Universal Constraint for Learning Optical Flow

Yi Xiao, Carlos Rodriguez Coronel, Jing Zhan +3

We propose triangular consistency as a first-principled constraint for optical flow, which is agnostic to network architecture, supervision type, and dataset, and applies to both i…

cs.CV2025

Test-Time Defense Against Adversarial Attacks via Stochastic Resonance of Latent Ensembles

Dong Lao, Yuxiang Zhang, Haniyeh Ehsani Oskouie +3

We propose a test-time defense mechanism against adversarial attacks: imperceptible image perturbations that significantly alter the predictions of a model. Unlike existing methods…

cs.CV2025

Divided Attention: Unsupervised Multi-Object Discovery with Contextually Separated Slots

Dong Lao, Zhengyang Hu, Francesco Locatello +2

We investigate the emergence of objects in visual perception in the absence of any semantic annotation. The resulting model has received no supervision, does not use any pre-traine…

cs.CV2024

RSA: Resolving Scale Ambiguities in Monocular Depth Estimators through Language Descriptions

Ziyao Zeng, Yangchao Wu, Hyoungseob Park +6

We propose a method for metric-scale monocular depth estimation. Inferring depth from a single image is an ill-posed problem due to the loss of scale from perspective projection du…