Related papers: EvRWKV: A Continuous Interactive RWKV Framework fo…
Current multispectral object detection methods often retain extraneous background or noise during feature fusion, limiting perceptual performance. To address this, we propose an innovative feature fusion framework based on cross-modal…
Robotic Vision-Language-Action (VLA) models generalize well for open-ended manipulation, but their perception is fragile under sensing-stage degradations such as extreme low light, motion blur, and black clipping. We present E-VLA, an…
Event cameras have attracted increasing attention in recent years due to their advantages in high dynamic range, high temporal resolution, low power consumption, and low latency. Some researchers have begun exploring pre-training directly…
Integrating event cameras with Multimodal Large Language Models (MLLMs) promises general scene understanding in challenging visual conditions, yet requires navigating a trade-off between preserving the unique advantages of event data and…
Style transfer aims to generate a new image preserving the content but with the artistic representation of the style source. Most of the existing methods are based on Transformers or diffusion models, however, they suffer from quadratic…
Recent video semantic segmentation (VSS) methods have demonstrated promising results in well-lit environments. However, their performance significantly drops in low-light scenarios due to limited visibility and reduced contextual details.…
Event cameras offer unique advantages for facial keypoint alignment under challenging conditions, such as low light and rapid motion, due to their high temporal resolution and robustness to varying illumination. However, existing RGB facial…
Object detection in autonomous driving is frequently compromised by complex illumination. While event cameras offer a robust solution, they are susceptible to sudden contrast changes such as reflections which often trigger dense, misleading…
We present a lightweight two-stage framework for low-light image enhancement (LLIE) that achieves competitive perceptual quality with significantly fewer parameters than existing methods. Our approach combines frozen algorithm-based…
Lightweight image super-resolution aims to reconstruct high-resolution images from low-resolution images using low computational costs. However, existing methods result in the loss of middle-layer features due to activation functions. To…
Event cameras respond to changes in log-brightness at the millisecond level, making them ideal for optical flow estimation. However, existing datasets from event cameras provide only low frame rate ground truth for optical flow, limiting…
Multi-exposure image fusion aims to generate a single high-dynamic image by integrating images with different exposures. Existing deep learning-based multi-exposure image fusion methods primarily focus on spatial domain fusion, neglecting…
Video frame interpolation, the process of synthesizing intermediate frames between sequential video frames, has made remarkable progress with the use of event cameras. These sensors, with microsecond-level temporal resolution, fill…
Infrared and visible image fusion (IVIF) is a fundamental task in multi-modal perception that aims to integrate complementary structural and textural cues from different spectral domains. In this paper, we propose FusionNet, a novel…
Although deep learning has advanced remote sensing change detection (RSCD), most methods rely solely on image modality, limiting feature representation, change pattern modeling, and generalization especially under illumination and noise…
Existing Visual Language Modelsoften struggle with information loss and limited reasoning abilities when handling high-resolution web interfaces that combine complex visual, textual, and interactive elements. These challenges are…
Continuous space-time video super-resolution (C-STVSR) endeavors to upscale videos simultaneously at arbitrary spatial and temporal scales, which has recently garnered increasing interest. However, prevailing methods struggle to yield…
Currently, most multimodal studies are based on large language models (LLMs) with quadratic-complexity Transformer architectures. While linear models like RNNs enjoy low inference costs, their application has been largely limited to the…
Vector quantization (VQ) transforms continuous image features into discrete representations, providing compressed, tokenized inputs for generative models. However, VQ-based frameworks suffer from several issues, such as non-smooth latent…
The field of advanced text-to-image generation is witnessing the emergence of unified frameworks that integrate powerful text encoders, such as CLIP and T5, with Diffusion Transformer backbones. Although there have been efforts to control…