English
Related papers

Related papers: MonoSDF: Exploring Monocular Geometric Cues for Ne…

200 papers

Depth estimation provides an alternative approach for perceiving 3D information in autonomous driving. Monocular depth estimation, whether with single-frame or multi-frame inputs, has achieved significant success by learning various types…

Computer Vision and Pattern Recognition · Computer Science 2023-12-06 Naiyu Fang , Lemiao Qiu , Shuyou Zhang , Zili Wang , Zheyuan Zhou , Kerui Hu

Neural 3D scene representations have shown great potential for 3D reconstruction from 2D images. However, reconstructing real-world captures of complex scenes still remains a challenge. Existing generic 3D reconstruction methods often…

Computer Vision and Pattern Recognition · Computer Science 2024-12-11 Fangjinhua Wang , Marie-Julie Rakotosaona , Michael Niemeyer , Richard Szeliski , Marc Pollefeys , Federico Tombari

In this paper, we study the problem of continuous 3D shape representations. The majority of existing successful methods are coordinate-based implicit neural representations. However, they are inefficient to render novel views or recover…

Computer Vision and Pattern Recognition · Computer Science 2023-12-19 Zhuoman Liu , Bo Yang , Yan Luximon , Ajay Kumar , Jinxi Li

We present a method that learns neural shadow fields which are neural scene representations that are only learnt from the shadows present in the scene. While traditional shape-from-shadow (SfS) algorithms reconstruct geometry from shadows,…

Computer Vision and Pattern Recognition · Computer Science 2022-07-21 Kushagra Tiwary , Tzofi Klinghoffer , Ramesh Raskar

Reconstructing detailed 3D scenes from single-view images remains a challenging task due to limitations in existing approaches, which primarily focus on geometric shape recovery, overlooking object appearances and fine shape details. To…

Computer Vision and Pattern Recognition · Computer Science 2023-11-02 Yixin Chen , Junfeng Ni , Nan Jiang , Yaowei Zhang , Yixin Zhu , Siyuan Huang

The reconstruction of indoor scenes from multi-view RGB images is challenging due to the coexistence of flat and texture-less regions alongside delicate and fine-grained regions. Recent methods leverage neural radiance fields aided by…

Computer Vision and Pattern Recognition · Computer Science 2024-08-14 Sheng Ye , Yubin Hu , Matthieu Lin , Yu-Hui Wen , Wang Zhao , Yong-Jin Liu , Wenping Wang

Reconstructing objects with realistic materials from multi-view images is problematic, since it is highly ill-posed. Although the neural reconstruction approaches have exhibited impressive reconstruction ability, they are designed for…

Graphics · Computer Science 2024-05-07 Jia Li , Lu Wang , Lei Zhang , Beibei Wang

A key contributor to recent progress in 3D detection from single images is monocular depth estimation. Existing methods focus on how to leverage depth explicitly, by generating pseudo-pointclouds or providing attention cues for image…

Computer Vision and Pattern Recognition · Computer Science 2022-10-07 Dennis Park , Jie Li , Dian Chen , Vitor Guizilini , Adrien Gaidon

The recent success of implicit neural scene representations has presented a viable new method for how we capture and store 3D scenes. Unlike conventional 3D representations, such as point clouds, which explicitly store scene properties in…

Computer Vision and Pattern Recognition · Computer Science 2021-01-19 Amit Kohli , Vincent Sitzmann , Gordon Wetzstein

Recently, Gaussian Splatting has sparked a new trend in the field of computer vision. Apart from novel view synthesis, it has also been extended to the area of multi-view reconstruction. The latest methods facilitate complete, detailed…

Computer Vision and Pattern Recognition · Computer Science 2025-01-09 Han Huang , Yulun Wu , Chao Deng , Ge Gao , Ming Gu , Yu-Shen Liu

Several variants of Neural Radiance Fields (NeRFs) have significantly improved the accuracy of synthesized images and surface reconstruction of 3D scenes/objects. In all of these methods, a key characteristic is that none can train the…

Computer Vision and Pattern Recognition · Computer Science 2025-06-11 Gonçalo Dias Pais , Valter Piedade , Moitreya Chatterjee , Marcus Greiff , Pedro Miraldo

We present a novel method for reconstructing a 3D implicit surface from a large-scale, sparse, and noisy point cloud. Our approach builds upon the recently introduced Neural Kernel Fields (NKF) representation. It enjoys similar…

Computer Vision and Pattern Recognition · Computer Science 2023-06-12 Jiahui Huang , Zan Gojcic , Matan Atzmon , Or Litany , Sanja Fidler , Francis Williams

Multi-view 3D surface reconstruction using neural implicit representations has made notable progress by modeling the geometry and view-dependent radiance fields within a unified framework. However, their effectiveness in reconstructing…

Computer Vision and Pattern Recognition · Computer Science 2024-09-12 Zijie Jiang , Tianhan Xu , Hiroharu Kato

In recent years, huge progress has been made on learning neural implicit representations from multi-view images for 3D reconstruction. As an additional input complementing coordinates, using sinusoidal functions as positional encodings…

Computer Vision and Pattern Recognition · Computer Science 2023-08-23 Sijia Jiang , Jing Hua , Zhizhong Han

Despite significant progress made in the past few years, challenges remain for depth estimation using a single monocular image. First, it is nontrivial to train a metric-depth prediction model that can generalize well to diverse scenes…

Computer Vision and Pattern Recognition · Computer Science 2022-09-07 Wei Yin , Jianming Zhang , Oliver Wang , Simon Niklaus , Simon Chen , Yifan Liu , Chunhua Shen

Neural rendering of implicit surfaces performs well in 3D vision applications. However, it requires dense input views as supervision. When only sparse input images are available, output quality drops significantly due to the shape-radiance…

Computer Vision and Pattern Recognition · Computer Science 2023-09-06 Haoyu Wu , Alexandros Graikos , Dimitris Samaras

3D Gaussian Splatting (3DGS) has emerged as a powerful technique for generating photorealistic renderings of a scene in real-time. However, the volumetric nature of 3DGS limits its ability to accurately capture surface geometry. To address…

Computer Vision and Pattern Recognition · Computer Science 2026-05-04 Prajwal Gupta C. R. , Divyam Sheth , Jinjoo Ha , Mirela Ostrek , Justus Thies

SDF-based differential rendering frameworks have achieved state-of-the-art multiview 3D shape reconstruction. In this work, we re-examine this family of approaches by minimally reformulating its core appearance model in a way that…

Computer Vision and Pattern Recognition · Computer Science 2025-03-26 Briac Toussaint , Diego Thomas , Jean-Sébastien Franco

In this paper, we investigate a new optimization framework for multi-view 3D shape reconstructions. Recent differentiable rendering approaches have provided breakthrough performances with implicit shape representations though they can still…

Computer Vision and Pattern Recognition · Computer Science 2023-03-06 Pierre Zins , Yuanlu Xu , Edmond Boyer , Stefanie Wuhrer , Tony Tung

This paper reports a new continuous 3D loss function for learning depth from monocular images. The dense depth prediction from a monocular image is supervised using sparse LIDAR points, which enables us to leverage available open source…

Computer Vision and Pattern Recognition · Computer Science 2020-08-11 Minghan Zhu , Maani Ghaffari , Yuanxin Zhong , Pingping Lu , Zhong Cao , Ryan M. Eustice , Huei Peng