Computer Vision

Variance Reduction Fine-tuning (VRF) simultaneously boosts in-distribution and out-of-distribution accuracy in fine-tuned zero-shot models, overcoming the ID-OOD trade-off.

RobIR: Robust inverse rendering in high-illumination scenes using ACES tone mapping and regularized visibility estimation for accurate BRDF reconstruction.

ROBIN: A novel watermarking method for diffusion models that actively conceals robust watermarks using adversarial optimization, enabling strong, imperceptible, and verifiable image authentication.

RLE: A novel data augmentation strategy unifying cross-spectral re-ID, significantly boosting model performance by mimicking local linear transformations.

GLMix: A novel vision backbone efficiently integrates convolutions and multi-head self-attention at different granularities, achieving state-of-the-art performance while addressing scalability issues.

RGB-Event tracker CSAM leverages MOT philosophy for enhanced robustness by integrating appearance and motion information from RGB and event streams, achieving state-of-the-art performance.

Researchers developed Camera-Agnostic Patch (CAP) attacks, improving adversarial patch reliability by simulating camera image processing in attacks against person detectors.

ReVideo enables precise local video editing by independently controlling content and motion, overcoming limitations of existing methods and paving the way for advanced video manipulation.

RETR: Multi-view radar detection transformer significantly improves indoor object detection and segmentation.

This paper presents a novel regional cross-attention module for rich-context layout-to-image generation, significantly improving image accuracy while addressing limitations of existing methods. Two n…

Researchers enhanced image generation by improving score distillation sampling via a novel Schrödinger Bridge framework, improving realism without computational overhead.

ImOOD tackles the challenge of imbalanced data distribution in OOD detection by introducing a generalized statistical framework and a unified regularization technique, leading to significant performan…

Revolutionizing image exposure assessment, Pixel-level IEA Network (P-IEANet) achieves state-of-the-art performance with a novel pixel-level approach, a new dataset (IEA40K), and a benchmark of 19 met…

WBSR: A novel framework for efficient image super-resolution that tackles data and model imbalances for superior performance and approximately a 34% reduction in computational cost.

DEPICT: A new white-box decoder for Transformer-based semantic segmentation, achieving better performance with fewer parameters by leveraging the principle of compression and connecting Transformer de…

RestoreAgent, an AI-powered image restoration agent, autonomously identifies and corrects multiple image degradations, exceeding human expert performance.

Resfusion, a novel framework, accelerates image restoration by integrating residual noise into the diffusion process, achieving superior results with fewer steps.

ReNO: Boost one-step text-to-image models by cleverly optimizing initial noise using reward signals, achieving state-of-the-art results efficiently.

Remix-DiT: Boosting diffusion model image generation quality by cleverly mixing smaller basis models into numerous specialized denoisers, improving efficiency and lowering costs!

Relationship Prompt Network (RPN) achieves state-of-the-art open-vocabulary semantic segmentation using only prompt learning and a Vision-Language Model (VLM), eliminating the need for expensive segme…