Results 71 to 80 of about 20,627 (197)

CSCGAN: Cross-Space Contrastive Learning for Blind Image Inpainting

Applied Sciences
Existing general image inpainting works require the user to customize a mask to indicate the region to be inpainted. However, the mask is often hard to calibrate accurately in real-world applications, e.g., graffiti removal.
Sheng Jin, Weijing Zhang, Tianyi Chu, Zhanjie Zhang, Lei Zhao, Wei Xing, Huaizhong Lin, Lixia Chen   +7 more
doaj   +1 more source

Progressive With Purpose: Guiding Progressive Inpainting DNNs Through Context and Structure

IEEE Access, 2023
The advent of deep learning in the past decade has significantly helped advance image inpainting. Although achieving promising performance, deep learning-based inpainting algorithms still struggle from the distortion caused by the fusion of structural ...
Kangdi Shi, Muhammad Alrabeiah, Jun Chen
doaj   +1 more source

PBR‐Inspired Controllable Diffusion for Image Generation

Computer Graphics Forum, EarlyView.
Abstract Despite recent advances in text‐to‐image generation, controlling geometric layout and PBR material properties in synthesized scenes remains challenging. We present a pipeline that first produces a G‐buffer (albedo, normals, depth, roughness, shading, and metallic) from a text prompt and then renders a final image through a PBR‐inspired branch ...
Bowen Xue, Giuseppe Claudio Guarnera, Shuang Zhao, Zahra Montazeri   +3 more
wiley   +1 more source

See4D: Pose‐Free 4D Generation via Auto‐Regressive Video Inpainting

Computer Graphics Forum, EarlyView.
Abstract Immersive applications call for synthesizing spatiotemporal 4D content from casual videos without costly 3D supervision. Existing video‐to‐4D methods typically rely on manually annotated camera poses, which are labor‐intensive and brittle for in‐the‐wild footage.
Dongyue Lu, Ao Liang, Tianxin Huang, Xiao Fu, Yuyang Zhao, Baorui Ma, Liang Pan, Wei Yin, Lingdong Kong, Wei Tsang Ooi, Ziwei Liu   +10 more
wiley   +1 more source

Lightweight Multi-Scales Feature Diffusion for Image Inpainting Towards Underwater Fish Monitoring

Journal of Marine Science and Engineering
In the process of gradually upgrading aquaculture to the information and intelligence industries, it is usually necessary to collect images of underwater fish.
Zhuowei Wang, Xiaoqi Jiang, Chong Chen, Yanxi Li   +3 more
doaj   +1 more source

Exploiting Multi-Direction Features in MRF-Based Image Inpainting Approaches

IEEE Access, 2019
Image inpainting technique recovers the missing regions of an image using information from known regions and it has shown success in various application fields.
Zhidan Li, Jiawei Liu, Jixiang Cheng
doaj   +1 more source

Low Dimensional Manifold Regularization Based Blind Image Inpainting and Non-Uniform Impulse Noise Recovery

IEEE Access, 2020
Blind image inpainting is a challenging task in image processing. Motivated by the excellent performance of low dimensional manifold model (LDMM) in image inpainting for large-scale pixels missing, we introduce a novel blind inpainting model to repair ...
Mei Gao, Baosheng Kang, Xiangchu Feng, Lixia Cao, Wenjuan Zhang   +4 more
doaj   +1 more source

TreeON: Reconstructing 3D Tree Point Clouds from Orthophotos and Heightmaps

Computer Graphics Forum, EarlyView.
Abstract We present TreeON, a novel neural‐based framework for reconstructing detailed 3D tree point clouds from sparse top‐down geodata, using only a single orthophoto and its corresponding Digital Surface Model (DSM). Our method introduces a new training supervision strategy that combines both geometric supervision and a differentiable shadow and ...
Angeliki Grammatikaki, Johannes Eschner, Pedro Hermosilla, Oscar Argudo, Manuela Waldner   +4 more
wiley   +1 more source

LeafFit: Plant Assets Creation from 3D Gaussian Splatting

Computer Graphics Forum, EarlyView.
Abstract We propose LeafFit, a pipeline that converts 3D Gaussian Splatting (3DGS) of individual plants into editable, instanced mesh assets. While 3DGS faithfully captures complex foliage, its high memory footprint and lack of mesh topology make it incompatible with traditional game production workflows. We address this by leveraging the repetition of
Chang Luo, Nobuyuki Umetani
wiley   +1 more source

Step2Motion: Locomotion Reconstruction from Pressure Sensing Insoles

Computer Graphics Forum, EarlyView.
Abstract Human motion is fundamentally driven by continuous physical interaction with the environment. Whether walking, running, or simply standing, the forces exchanged between our feet and the ground provide crucial insights for understanding and reconstructing human movement. Recent advances in wearable insole devices offer a compelling solution for
J. L. Ponton, E. Alvarado, L. G. Foo, N. Pelechano, C. Andujar, M. Habermann   +5 more
wiley   +1 more source