Tag: computer vision
Browse our exclusive articles!
CDH-Bench: Evaluating Visual Fidelity in Vision-Language Models
Discover CDH-Bench, a benchmark assessing commonsense-driven hallucinations to improve visual fidelity in vision-language models.
CoCoDiff: Fine-Grained Semantic Style Transfer Model
Discover CoCoDiff, a training-free diffusion model for fine-grained, semantic-consistent style transfer with superior visual quality and pixel-level alignm...
GPERT: Advanced Event-Based 3D Gaussian Ray Tracing
Discover GPERT, a cutting-edge framework for event-based 3D Gaussian ray tracing that boosts accuracy and speed in 3D reconstruction without prior models.
Robust Object Representation with Two-Stage Vision Transformers
Discover how two-stage Vision Transformers and hard masking improve object representation robustness against contextual biases and out-of-distribution data...
Efficient CLIP Adaptation for Accurate Monocular Depth Estimation
Discover MoA-DepthCLIP, a lightweight framework using prompt-guided CLIP adaptation to improve monocular depth estimation with minimal supervision.