Zobrazeno 1 - 10
of 297
pro vyhledávání: '"Wen, Bihan"'
Recent advancements in deep learning have shown impressive results in image and video denoising, leveraging extensive pairs of noisy and noise-free data for supervision. However, the challenge of acquiring paired videos for dynamic scenes hampers the
Externí odkaz:
http://arxiv.org/abs/2409.11256
Recent advancements in deep learning have yielded promising results for the image shadow removal task. However, most existing methods rely on binary pre-generated shadow masks. The binary nature of such masks could potentially lead to artifacts near
Externí odkaz:
http://arxiv.org/abs/2409.07041
The integration of miniaturized spectrometers into mobile devices offers new avenues for image quality enhancement and facilitates novel downstream tasks. However, the broader application of spectral sensors in mobile photography is hindered by the i
Externí odkaz:
http://arxiv.org/abs/2407.17996
Despite significant progress in 3D point cloud segmentation, existing methods primarily address specific tasks and depend on explicit instructions to identify targets, lacking the capability to infer and understand implicit user intentions in a unifi
Externí odkaz:
http://arxiv.org/abs/2407.13761
Autor:
Guo, Laniqng, Wang, Chong, Wang, Yufei, Yu, Yi, Huang, Siyu, Yang, Wenhan, Kot, Alex C., Wen, Bihan
Shadow removal aims at restoring the image content within shadow regions, pursuing a uniform distribution of illumination that is consistent between shadow and non-shadow regions. {Comparing to other image restoration tasks, there are two unique chal
Externí odkaz:
http://arxiv.org/abs/2407.08865
Concept bottleneck models (CBMs), which predict human-interpretable concepts (e.g., nucleus shapes in cell images) before predicting the final output (e.g., cell type), provide insights into the decision-making processes of the model. However, traini
Externí odkaz:
http://arxiv.org/abs/2407.06600
Novel view synthesis from raw images provides superior high dynamic range (HDR) information compared to reconstructions from low dynamic range RGB images. However, the inherent noise in unprocessed raw images compromises the accuracy of 3D scene repr
Externí odkaz:
http://arxiv.org/abs/2406.08300
Recently, 3D Gaussian Splatting (3DGS) has become a promising framework for novel view synthesis, offering fast rendering speeds and high fidelity. However, the large number of Gaussians and their associated attributes require effective compression t
Externí odkaz:
http://arxiv.org/abs/2405.20721
Blind image quality assessment (IQA) in the wild, which assesses the quality of images with complex authentic distortions and no reference images, presents significant challenges. Given the difficulty in collecting large-scale training data, leveragi
Externí odkaz:
http://arxiv.org/abs/2405.19996
Diffusion-based models for story visualization have shown promise in generating content-coherent images for storytelling tasks. However, how to effectively integrate new characters into existing narratives while maintaining character consistency rema
Externí odkaz:
http://arxiv.org/abs/2405.11852