[2606.03287] BA-T: An Iterative Transformer for Two-View Bundle Adjustment
Abstract page for arXiv paper 2606.03287: BA-T: An Iterative Transformer for Two-View Bundle Adjustment
America Forever Bytes
Other
Abstract page for arXiv paper 2606.03287: BA-T: An Iterative Transformer for Two-View Bundle Adjustment
Abstract page for arXiv paper 2606.03493: Low-Frequency Shortcuts in Texture-Driven Visual Learning
Abstract page for arXiv paper 2606.03540: Attend to Anything: Foundation Model for Unified Human Attention Modeling
Human gaze behaviour provides insights into the mental processes underlying the execution of a task. As reading involves visual sampling and language proce
Abstract page for arXiv paper 2606.01710: Density-Aware Translation of Spurious Correlations in Zero-Shot VLMs
Abstract page for arXiv paper 2605.30818: GaMi: Geometry-Agnostic Material Identification via Cross-Modal Subtractive Disentanglement
Abstract page for arXiv paper 2605.31041: Does Visual Information Play a Decisive Role in Vision-Language-Action Model Driving Behavior?
Mammals aren’t known for the ocular regenerative powers, but a study shows that nature has a few tricks up its sleeve.
The human eye does not actually see purple, as purple is not a color on the visual spectrum, scientists say. Here's what's actually happening.
Researchers found that when they gave a sewing-machine worker with age-related vision loss a pair of glasses, it led to a 6% increase in productivity.
Abstract page for arXiv paper 2604.00913: Benchmarking and Mechanistic Analysis of Vision-Language Models for Cross-Depiction Assembly Instruction Alignment
Abstract page for arXiv paper 2605.28609: JECA^2: Judgment-Explanation Consistent Adversarial Attack against Forensic Vision-Language Models
Abstract page for arXiv paper 2605.28087: Whose Is This?: Context-Aware Object Ownership Inference with Uncertainty-Guided Questioning