Relightable 3d gaussians: Realistic point cloud relighting with brdf decomposition and ray tracing

J Gao, C Gu, Y Lin, Z Li, H Zhu, X Cao, L Zhang… - … on Computer Vision, 2024 - Springer
In this paper, we present a novel differentiable point-based rendering framework to achieve
photo-realistic relighting. To make the reconstructed scene relightable, we enhance vanilla …

Dust3r: Geometric 3d vision made easy

S Wang, V Leroy, Y Cabon… - Proceedings of the …, 2024 - openaccess.thecvf.com
Multi-view stereo reconstruction (MVS) in the wild requires to first estimate the camera
intrinsic and extrinsic parameters. These are usually tedious and cumbersome to obtain yet …

High-frequency stereo matching network

H Zhao, H Zhou, Y Zhang, J Chen… - Proceedings of the …, 2023 - openaccess.thecvf.com
In the field of binocular stereo matching, remarkable progress has been made by iterative
methods like RAFT-Stereo and CREStereo. However, most of these methods lose …

Direct2. 5: Diverse text-to-3d generation via multi-view 2.5 d diffusion

Y Lu, J Zhang, S Li, T Fang… - Proceedings of the …, 2024 - openaccess.thecvf.com
Recent advances in generative AI have unveiled significant potential for the creation of 3D
content. However current methods either apply a pre-trained 2D diffusion model with the …

[HTML][HTML] Deep learning based multi-view stereo matching and 3D scene reconstruction from oblique aerial images

J Liu, J Gao, S Ji, C Zeng, S Zhang, JY Gong - ISPRS Journal of …, 2023 - Elsevier
In this paper, we propose a practical three-dimensional (3D) real-scene reconstruction
framework named Deep3D, which is paired with a deep learning based multi-view stereo …

[HTML][HTML] A general deep learning based framework for 3D reconstruction from multi-view stereo satellite images

J Gao, J Liu, S Ji - ISPRS Journal of Photogrammetry and Remote …, 2023 - Elsevier
In this paper, we propose a general deep learning based framework, named Sat-MVSF, to
perform three-dimensional (3D) reconstruction of the Earth's surface from multi-view optical …

EmoTalk3D: high-fidelity free-view synthesis of emotional 3D talking head

Q He, X Ji, Y Gong, Y Lu, Z Diao, L Huang… - … on Computer Vision, 2024 - Springer
We present a novel approach for synthesizing 3D talking heads with controllable emotion,
featuring enhanced lip synchronization and rendering quality. Despite significant progress in …

Learnable cost metric-based multi-view stereo for point cloud reconstruction

G Yang, X Zhou, C Gao, X Chen… - IEEE Transactions on …, 2023 - ieeexplore.ieee.org
3-D reconstruction is essential to defect localization. This article proposes LCM-MVSNet, a
novel multi-view stereo (MVS) network with learnable cost metric (LCM) for more accurate …

MoCha-Stereo: Motif Channel Attention Network for Stereo Matching

Z Chen, W Long, H Yao, Y Zhang… - Proceedings of the …, 2024 - openaccess.thecvf.com
Learning-based stereo matching techniques have made significant progress. However
existing methods inevitably lose geometrical structure information during the feature channel …

Robust training for multi-view stereo networks with noisy labels

X Wang, H Luo, Z Wang, J Zheng, X Bai - Displays, 2024 - Elsevier
Recent multi-view stereo (MVS) works benefit a lot from deep neural networks with their
great representation ability. However, top-performing networks require accurate depth …