Computer Vision

Vivid-ZOO: Generating high-quality multi-view videos from text using a novel diffusion model.

This paper presents NSP², a novel method for visual prompt tuning in continual learning that leverages orthogonal projection to prevent catastrophic forgetting by tuning prompts orthogonal to previous…

Visual pinwheel centers in the cortex act as efficient geometric saliency detectors, responding faster and stronger to complex spatial textures than other structures.

Visual Fourier Prompt Tuning (VFPT) leverages the Fast Fourier Transform to seamlessly integrate spatial and frequency information for superior parameter-efficient vision model fine-tuning, even with …

Researchers developed a novel zero-shot EEG-based framework for visual reconstruction using a tailored brain encoder and a two-stage image generation strategy, achieving state-of-the-art performance i…

CONBIAS tackles dataset bias by representing visual data as concept graphs, diagnosing imbalances via clique analysis, and debiasing through targeted data augmentation for improved model generalizatio…

OoD-ViT-NAS: a new benchmark reveals how ViT architecture impacts out-of-distribution generalization, highlighting the importance of embedding dimension and challenging the reliance on in-distribution…

Vision Mamba Mender systematically optimizes the Mamba model by identifying and repairing internal and external state flaws, significantly improving its performance in visual recognition tasks.

VFM-6D: a novel framework achieving generalizable object pose estimation for unseen categories by leveraging vision-language models.

Unsupervised learning framework enables high-fidelity non-line-of-sight (NLOS) imaging from irregularly undersampled transients, surpassing state-of-the-art methods in speed and robustness.

Researchers boost long-form video understanding efficiency by 6.89x and reduce memory usage by 84% using a novel learnable video token merging algorithm.

Training-free video motion control achieved via novel Motion Feature (MOFT) extraction from existing video diffusion models, offering architecture-agnostic insights and high performance.

VFIMamba uses state-space models for efficient and dynamic video frame interpolation, achieving state-of-the-art results by introducing a novel Mixed-SSM Block and curriculum learning.

VCR-GauS: Novel view-consistent depth-normal regularizer for superior, real-time 3D surface reconstruction using Gaussian splatting.

New uncertainty estimation method for 3D Gaussian Splatting improves scene reconstruction quality by leveraging variational multi-scale representation and efficiently removing noisy data.

UV3-TeD generates high-quality 3D textures directly on object surfaces using a novel diffusion probabilistic model, eliminating UV-mapping limitations.

UPS: A novel algorithm for lightweight single-image super-resolution, decoupling feature extraction and similarity modeling for enhanced efficiency and robustness.

Boosting 3D medical image segmentation, a novel U-shaped Connection (uC) integrates 2D U-Net skip connections into 3D CNNs, improving axial-slice plane feature extraction, surpassing state-of-the-art …

Vision Transformers (ViTs) generalize surprisingly well, even when overfitting training data; this work provides the first theoretical explanation by characterizing the optimization dynamics of ViTs a…

Untrained neural networks revolutionize snapshot compressive imaging (SCI) by enabling high-dimensional data recovery from a single 2D measurement, achieving state-of-the-art results without needing e…