English
Related papers

Related papers: Training-free Spatially Grounded Geometric Shape E…

200 papers

Robust 3D representation learning forms the perceptual foundation of spatial intelligence, enabling downstream tasks in scene understanding and embodied AI. However, learning such representations directly from unposed multi-view images…

Computer Vision and Pattern Recognition · Computer Science 2026-04-14 Bo Zhou , Qiuxia Lai , Zeren Sun , Xiangbo Shu , Yazhou Yao , Wenguan Wang

Code embedding is a keystone in the application of machine learning on several Software Engineering (SE) tasks. To effectively support a plethora of SE tasks, the embedding needs to capture program syntax and semantics in a way that is…

Software Engineering · Computer Science 2022-01-24 Wei Ma , Mengjie Zhao , Ezekiel Soremekun , Qiang Hu , Jie Zhang , Mike Papadakis , Maxime Cordy , Xiaofei Xie , Yves Le Traon

Automatic segmentation of fine-grained brain structures remains a challenging task. Current segmentation methods mainly utilize 2D and 3D deep neural networks. The 2D networks take image slices as input to produce coarse segmentation in…

Computer Vision and Pattern Recognition · Computer Science 2019-05-08 Yuemeng Li , Hangfan Liu , Hongming Li , Yong Fan

Grokking -- the abrupt transition from memorization to generalization after extended training -- has been linked to the emergence of low-dimensional structure in learning dynamics. Yet neural network parameters inhabit extremely…

Machine Learning · Computer Science 2026-02-24 Yongzhong Xu

We present a new approach to 3D object representation where a neural network encodes the geometry of an object directly into the weights and biases of a second 'mapping' network. This mapping network can be used to reconstruct an object by…

Machine Learning · Computer Science 2020-04-07 Eric Mitchell , Selim Engin , Volkan Isler , Daniel D Lee

Transformer-based detectors have advanced small-object detection, but they often remain inefficient and vulnerable to background-induced query noise, which motivates deep decoders to refine low-quality queries. We present HELP…

Computer Vision and Pattern Recognition · Computer Science 2026-04-17 Yangchen Zeng , Zhenyu Yu , Dongming Jiang , Wenbo Zhang , Yifan Hong , Zhanhua Hu , Jiao Luo , Kangning Cui

Cone Beam Computed Tomography (CBCT) plays a vital role in clinical imaging. Traditional methods typically require hundreds of 2D X-ray projections to reconstruct a high-quality 3D CBCT image, leading to considerable radiation exposure.…

Image and Video Processing · Electrical Eng. & Systems 2024-10-08 Zhentao Liu , Yu Fang , Changjian Li , Han Wu , Yuan Liu , Dinggang Shen , Zhiming Cui

Recent image generation models show remarkable generation performance. However, they mirror strong location preference in datasets, which we call spatial bias. Therefore, generators render poor samples at unseen locations and scales. We…

Machine Learning · Computer Science 2021-08-04 Jooyoung Choi , Jungbeom Lee , Yonghyun Jeong , Sungroh Yoon

We present SAGNet, a structure-aware generative model for 3D shapes. Given a set of segmented objects of a certain class, the geometry of their parts and the pairwise relationships between them (the structure) are jointly learned and…

Graphics · Computer Science 2019-11-15 Zhijie Wu , Xiang Wang , Di Lin , Dani Lischinski , Daniel Cohen-Or , Hui Huang

Image-based volumetric humans using pixel-aligned features promise generalization to unseen poses and identities. Prior work leverages global spatial encodings and multi-view geometric consistency to reduce spatial ambiguity. However,…

Computer Vision and Pattern Recognition · Computer Science 2022-07-22 Marko Mihajlovic , Aayush Bansal , Michael Zollhoefer , Siyu Tang , Shunsuke Saito

Positional encoding plays a pivotal role in determin?ing the extrapolation and generalization performance of wireless foundation models for channel state information (CSI) modeling, latent characterization, and task-specific prediction.…

Signal Processing · Electrical Eng. & Systems 2026-05-05 Chenyu Zhang , Xinchen Lyu , Chenshan Ren , Shuhan Liu , Qimei Cui

Geometric disentanglement, the separation of latent codes for intrinsic (i.e. identity) and extrinsic(i.e. pose) geometry, is a prominent task for generative models of non-Euclidean data such as 3D deformable models. It provides greater…

Computer Vision and Pattern Recognition · Computer Science 2020-12-14 N. Joseph Tatro , Stefan C. Schonsheck , Rongjie Lai

We propose a method for self-supervised image representation learning under the guidance of 3D geometric consistency. Our intuition is that 3D geometric consistency priors such as smooth regions and surface discontinuities may imply…

Computer Vision and Pattern Recognition · Computer Science 2022-03-30 Nenglun Chen , Lei Chu , Hao Pan , Yan Lu , Wenping Wang

Establishing correspondences from image to 3D has been a key task of 6DoF object pose estimation for a long time. To predict pose more accurately, deeply learned dense maps replaced sparse templates. Dense methods also improved pose…

Computer Vision and Pattern Recognition · Computer Science 2022-03-31 Yongzhi Su , Mahdi Saleh , Torben Fetzer , Jason Rambach , Nassir Navab , Benjamin Busam , Didier Stricker , Federico Tombari

Learning latent representations of registered meshes is useful for many 3D tasks. Techniques have recently shifted to neural mesh autoencoders. Although they demonstrate higher precision than traditional methods, they remain unable to…

Computer Vision and Pattern Recognition · Computer Science 2020-10-22 Yi Zhou , Chenglei Wu , Zimo Li , Chen Cao , Yuting Ye , Jason Saragih , Hao Li , Yaser Sheikh

Industrial CAD workflows require robust, generalizable 3D geometric representations supporting accuracy and explainability. We introduce Shape, a self-supervised foundation model converting surface meshes into dense per-token embeddings.…

Computer Vision and Pattern Recognition · Computer Science 2026-04-28 Bayangmbe Mounmo , Sam Chien , Mile Mitrovic

We introduce Perception Encoder (PE), a state-of-the-art vision encoder for image and video understanding trained via simple vision-language learning. Traditionally, vision encoders have relied on a variety of pretraining objectives, each…

Positional encodings (PEs) are essential for building powerful and expressive graph neural networks and graph transformers, as they effectively capture the relative spatial relationships between nodes. Although extensive research has been…

Machine Learning · Computer Science 2026-03-16 Yinan Huang , Haoyu Wang , Pan Li

Scalable coding, which can adapt to channel bandwidth variation, performs well in today's complex network environment. However, most existing scalable compression methods face two challenges: reduced compression performance and insufficient…

Image and Video Processing · Electrical Eng. & Systems 2024-12-03 Yongqi Zhai , Yi Ma , Luyang Tang , Wei Jiang , Ronggang Wang

Neural implicit surface reconstruction has become a new trend in reconstructing a detailed 3D shape from images. In previous methods, however, the 3D scene is only encoded by the MLPs which do not have an explicit 3D structure. To better…

Computer Vision and Pattern Recognition · Computer Science 2024-08-06 Xiaodong Gu , Weihao Yuan , Heng Li , Zilong Dong , Ping Tan
‹ Prev 1 3 4 5 6 7 10 Next ›