8 papers · 1 filter
Spatial-IQ: Deconstructing Spatial Intelligence via Hierarchical Capability Tests
Patrick Rim, Tom Long, Ekta Prashnani +6
Multimodal large language models (MLLMs) excel at visual interpretation but fail on spatial reasoning tasks that humans solve reliably. Existing benchmarks evaluate these models as…
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…
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…
Iris: Integrating Language into Diffusion-based Monocular Depth Estimation
Ziyao Zeng, Jingcheng Ni, Daniel Wang +5
Traditional monocular depth estimation suffers from inherent ambiguity and visual nuisances. We demonstrate that language can enhance monocular depth estimation by providing an add…
Diffeomorphic Template Registration for Atmospheric Turbulence Mitigation
Dong Lao, Congli Wang, Alex Wong +1
We describe a method for recovering the irradiance underlying a collection of images corrupted by atmospheric turbulence. Since supervised data is often technically impossible to o…
WorDepth: Variational Language Prior for Monocular Depth Estimation
Ziyao Zeng, Daniel Wang, Fengyu Yang +6
Three-dimensional (3D) reconstruction from a single image is an ill-posed problem with inherent ambiguities, i.e. scale. Predicting a 3D scene from text description(s) is similarly…