English
Related papers

Related papers: High-fidelity 3D Model Compression based on Key Sp…

200 papers

Real-time 3D reconstruction from RGB-D sensor data plays an important role in many robotic applications, such as object modeling and mapping. The popular method of fusing depth information into a truncated signed distance function (TSDF)…

Computer Vision and Pattern Recognition · Computer Science 2019-08-15 Malte Splietker , Sven Behnke

Indoor scenes we are living in are visually homogenous or textureless, while they inherently have structural forms and provide enough structural priors for 3D scene reconstruction. Motivated by this fact, we propose a structure-aware online…

Robotics · Computer Science 2024-03-26 Jaehoon Jang , Inha Lee , Minje Kim , Kyungdon Joo

Implicit Neural Representations (INRs) have been demonstrated to achieve state-of-the-art compression of a broad range of modalities such as images, videos, 3D surfaces, and audio. Most studies have focused on building neural counterparts…

Computational Geometry · Computer Science 2025-12-19 Sai Karthikey Pentapati , Gregoire Phillips , Alan Bovik

Extracting surfaces from Signed Distance Fields (SDFs) can be accomplished using traditional algorithms, such as Marching Cubes. However, since they rely on sign flips across the surface, these algorithms cannot be used directly on Unsigned…

Computer Vision and Pattern Recognition · Computer Science 2024-10-29 Federico Stella , Nicolas Talabot , Hieu Le , Pascal Fua

We propose a new method for compressing physics foundation models (PFMs) which is a new trend in AI for Science. While model compression is essential for reducing memory use and accelerating inference in large foundation models, it remains…

Machine Learning · Computer Science 2026-05-19 Chengjie Hong , Feixiang He , Yiheng Zeng , Lulu Kang , He Wang

Reconstructing hand-held objects from a single RGB image is an important and challenging problem. Existing works utilizing Signed Distance Fields (SDF) reveal limitations in comprehensively capturing the complex hand-object interactions,…

Computer Vision and Pattern Recognition · Computer Science 2023-10-27 Chenyangguang Zhang , Yan Di , Ruida Zhang , Guangyao Zhai , Fabian Manhardt , Federico Tombari , Xiangyang Ji

We present KDFNet, a novel method for 6D object pose estimation from RGB images. To handle occlusion, many recent works have proposed to localize 2D keypoints through pixel-wise voting and solve a Perspective-n-Point (PnP) problem for pose…

Computer Vision and Pattern Recognition · Computer Science 2021-09-22 Xingyu Liu , Shun Iwase , Kris M. Kitani

The medial axis, a lower-dimensional descriptor that captures the extrinsic structure of a shape, plays an important role in digital geometry processing. Despite its importance, computing the medial axis transform robustly from diverse…

Computer Vision and Pattern Recognition · Computer Science 2026-02-05 Jiayi Kong , Chen Zong , Jun Luo , Shiqing Xin , Fei Hou , Hanqing Jiang , Chen Qian , Ying He

Reconstructing three-dimensional (3D) structures from two-dimensional (2D) X-ray images is a valuable and efficient technique in medical applications that requires less radiation exposure than computed tomography scans. Recent approaches…

Image and Video Processing · Electrical Eng. & Systems 2025-03-11 Chengrui Zhu , Ryoichi Ishikawa , Masataka Kagesawa , Tomohisa Yuzawa , Toru Watsuji , Takeshi Oishi

Humans rely on their visual and tactile senses to develop a comprehensive 3D understanding of their physical environment. Recently, there has been a growing interest in exploring and manipulating objects using data-driven approaches that…

Computer Vision and Pattern Recognition · Computer Science 2023-11-22 Mauro Comi , Yijiong Lin , Alex Church , Alessio Tonioni , Laurence Aitchison , Nathan F. Lepora

Previous multi-view normal integration methods typically sample a single ray per pixel, without considering the spatial area covered by each pixel, which varies with camera intrinsics and the camera-to-object distance. Consequently, when…

Computer Vision and Pattern Recognition · Computer Science 2026-03-24 Tongyu Yang , Heng Guo , Yasuyuki Matsushita , Fumio Okura , Yu Luo , Xin Fan

In recent years, implicit surface representations through neural networks that encode the signed distance have gained popularity and have achieved state-of-the-art results in various tasks (e.g. shape representation, shape reconstruction,…

Graphics · Computer Science 2023-01-30 Petros Tzathas , Petros Maragos , Anastasios Roussos

We present a novel 3D shape completion framework that unifies multimodal conditioning, leveraging both 2D images and 3D partial scans through a latent diffusion model. Shapes are represented as Truncated Signed Distance Functions (TSDFs)…

Computer Vision and Pattern Recognition · Computer Science 2025-09-03 Simon Schaefer , Juan D. Galvis , Xingxing Zuo , Stefan Leutengger

We present a novel approach for recovering 3D shape and view dependent appearance from a few colored images, enabling efficient 3D reconstruction and novel view synthesis. Our method learns an implicit neural representation in the form of a…

Computer Vision and Pattern Recognition · Computer Science 2024-07-22 Mae Younes , Amine Ouasfi , Adnane Boukhayma

A signed distance function (SDF) parametrized by an MLP is a common ingredient of neural surface reconstruction. We build on the successful recent method NeuS to extend it by three new components. The first component is to borrow the…

Computer Vision and Pattern Recognition · Computer Science 2023-05-10 Yiqun Wang , Ivan Skorokhodov , Peter Wonka

Neural implicit 3D reconstruction can reproduce shapes without 3D supervision, and it learns the 3D scene through volume rendering methods and neural implicit representations. Current neural surface reconstruction methods tend to randomly…

Computer Vision and Pattern Recognition · Computer Science 2025-05-07 Shikun Zhang , Yiqun Wang , Cunjian Chen , Yong Li , Qiuhong Ke

Human hands are highly articulated and versatile at handling objects. Jointly estimating the 3D poses of a hand and the object it manipulates from a monocular camera is challenging due to frequent occlusions. Thus, existing methods often…

Computer Vision and Pattern Recognition · Computer Science 2024-02-28 Haozhe Qi , Chen Zhao , Mathieu Salzmann , Alexander Mathis

Localization of a robotic system within a previously mapped environment is important for reducing estimation drift and for reusing previously built maps. Existing techniques for geometry-based localization have focused on the description of…

Reconstructing complex structures from planar cross-sections is a challenging problem, with wide-reaching applications in medical imaging, manufacturing, and topography. Out-of-the-box point cloud reconstruction methods can often fail due…

Computer Vision and Pattern Recognition · Computer Science 2025-03-26 Thomas Walker , Salvatore Esposito , Daniel Rebain , Amir Vaxman , Arno Onken , Changjian Li , Oisin Mac Aodha

In visual computing, 3D geometry is represented in many different forms including meshes, point clouds, voxel grids, level sets, and depth images. Each representation is suited for different tasks thus making the transformation of one…

Computer Vision and Pattern Recognition · Computer Science 2022-09-02 Trevor Houchens , Cheng-You Lu , Shivam Duggal , Rao Fu , Srinath Sridhar