Computer Vision

ReGS: Real-time reference-based 3D scene stylization using Gaussian Splatting for high-fidelity texture editing and free-view navigation.

ReFIR enhances Large Restoration Models’ accuracy by incorporating retrieved images as external knowledge, mitigating hallucination without retraining.

RefDrop: A training-free method enhances image and video generation consistency by directly controlling the influence of reference features on the diffusion process, enabling precise manipulation of c…

ReF-LDM uses reference images to improve the accuracy of face image restoration, achieving high-quality results faithful to the subject’s true appearance.

SynCx, a novel recurrent autoencoder with complex weights, surpasses state-of-the-art models in unsupervised object discovery by iteratively refining phase relationships to achieve robust object bindi…

RectifID personalizes image generation by cleverly guiding a diffusion model using off-the-shelf classifiers, achieving identity preservation without needing extra training data.

Boost skeleton action recognition accuracy across datasets by recovering complete actions and resampling; outperforms existing methods.

Researchers developed a novel method for reconstructing the 3D shape of manipulated garments, achieving superior accuracy compared to existing techniques, particularly for complex, non-rigid deformati…

SRStitcher revolutionizes image stitching by integrating fusion and rectangling into a unified inpainting model, eliminating model training and achieving superior performance and stability.

RealCompo: A novel training-free framework dynamically balances realism and compositionality in text-to-image generation, achieving state-of-the-art results.

StreamDSGN: a real-time stereo 3D object detection framework significantly boosts streaming perception accuracy by leveraging historical information, a feature-flow fusion method, and a motion consist…

ECP-ViT: Real-time Vision Transformer on Mobile Devices via Core-Periphery Attention and Smart Data Layout.

RAW: A novel watermark framework ensures the authenticity of AI-generated images by embedding learnable watermarks directly into the image data, providing provable guarantees even under adversarial at…

RAMP: A novel training framework significantly boosts DNN robustness against diverse adversarial attacks by mitigating accuracy-robustness tradeoffs and improving generalization.

QUEEN: A novel framework for quantized and efficient streaming of free-viewpoint videos achieving high compression, quality, and speed.

This paper introduces a novel three-phase neural network framework that significantly enhances the quality of polarimetric images by complementarily fusing degraded noisy and blurry snapshots, preserv…

QuadMamba: A novel vision model leveraging quadtree-based scanning for superior performance in visual tasks, achieving state-of-the-art results with linear-time complexity.

QT-ViT boosts Vision Transformer efficiency by using quadratic Taylor expansion to approximate self-attention, achieving state-of-the-art accuracy and speed.

PuLID: Lightning-fast, tuning-free ID customization for text-to-image!

PTQ4DiT achieves 8-bit and even 4-bit weight precision for Diffusion Transformers, significantly improving efficiency for image generation without sacrificing quality.