SVGDreamer++: Advancing Editability and Diversity in Text-Guided SVG Generation [0.03%]
SVGDreamer++: 提升文本引导SVG生成的可编辑性和多样性
Ximing Xing,Qian Yu,Chuang Wang et al.
Ximing Xing et al.
Recently, text-guided scalable vector graphics (SVG) synthesis has shown great promise in domains like iconography and sketching. However, existing Text-to-SVG methods often face challenges in editability, visual quality, and diversity. To ...
Pixel2Pixel: A Pixelwise Approach for Zero-Shot Single Image Denoising [0.03%]
像素对像素：一种用于零样本单图像去噪的基于像素的方法
Qing Ma,Junjun Jiang,Xiong Zhou et al.
Qing Ma et al.
We propose Pixel2Pixel, a novel zero-shot image denoising framework that leverages the non-local self-similarity of images to generate a large number of training samples using only the input noisy image. This framework employs a compact con...
S-NeRF++: Autonomous Driving Simulation via Neural Reconstruction and Generation [0.03%]
S-NeRF++: 通过神经重建和生成实现自主驾驶仿真
Yurui Chen,Junge Zhang,Ziyang Xie et al.
Yurui Chen et al.
Autonomous driving simulation system plays a crucial role in enhancing self-driving data and simulating complex and rare traffic scenarios, ensuring navigation safety. However, traditional simulation systems, which often heavily rely on man...
Heterogeneous Correlation Aware Regularization for Sequential Confidence Calibration [0.03%]
异构相关性感知正则化在序列置信校准中的应用
Zhenghua Peng,Tianshui Chen,Shuangping Huang et al.
Zhenghua Peng et al.
Despite notable advancements across various tasks, deep sequence recognition models are shown to grapple with the dilemma of over-confidence, leading to unreliable predicted confidence, necessitating the need for calibration. Current effort...
Instruct-ReID++: Towards Universal Purpose Instruction-Guided Person Re-identification [0.03%]
Instruct-ReID++:迈向通用目的指令引导人物重新识别
Weizhen He,Yiheng Deng,Yunfeng Yan et al.
Weizhen He et al.
Recently, person re-identification (ReID) has witnessed fast development due to its broad practical applications and proposed various settings, e.g., traditional ReID, clothes-changing ReID, and visible-infrared ReID. However, current studi...
Convection-Diffusion Equation: a Theoretically Certified Framework for Neural Networks [0.03%]
对流扩散方程：神经网络的理论认证框架
Tangjun Wang,Chenglong Bao,Zuoqiang Shi
Tangjun Wang
Differential equations have demonstrated intrinsic connections to network structures, linking discrete network layers through continuous equations. Most existing approaches focus on the interaction between ordinary differential equations (O...
Ze-Xin Yin,Peng-Yi Jiao,Jiaxiong Qiu et al.
Ze-Xin Yin et al.
Existing Neural Radiance Fields (NeRF) methods suffer from the existence of reflective objects, often resulting in blurry or distorted rendering. Instead of calculating a single radiance field, we propose a multi-space neural radiance field...
Implicit Shape and Appearance Priors for Few-Shot Full Head Reconstruction [0.03%]
面向少样本完整人脸重建的隐式形状和外观先验
Pol Caselles,Eduard Ramon,Jaime Garcia et al.
Pol Caselles et al.
Recent advancements in learning techniques that employ coordinate-based neural representations have yielded remarkable results in multi-view 3D reconstruction tasks. However, these approaches often require a substantial number of input view...
Improving Adversarial Training from the Perspective of Class-Flipping Distribution [0.03%]
从类翻转分布的角度改进对抗训练
Dawei Zhou,Nannan Wang,Tongliang Liu et al.
Dawei Zhou et al.
Adversarial training has been proposed and widely recognized as a very effective method to defend against adversarial noise. However, the label flipping pattern on different classes still need deeper exploration to identify potential proble...
Temporally-Consistent Surface Reconstruction using Metrically-Consistent Atlases [0.03%]
使用度量一致的图谱进行时间一致的表面重建
Jan Bednarik,Noam Aigerman,Vladimir G Kim et al.
Jan Bednarik et al.
We propose a method for unsupervised reconstruction of a temporally-consistent sequence of surfaces from a sequence of time-evolving point clouds. It yields dense and semantically meaningful correspondences between frames. We represent the ...