2

DP-Adapter: Dual-pathway adapter for boosting fidelity and text consistency in customizable human image generation
We propose DP-Adapter, a dual-pathway adapter framework that enhances both fidelity and text consistency in customizable human image generation tasks.
Ye Wang * , Ruiqi Liu * , Xuping Xie, Lanjun Wang, Zili Yi, Rui Ma #
PDF Cite
DP-Adapter: Dual-pathway adapter for boosting fidelity and text consistency in customizable human image generation
Nav2Scene: Navigation-driven fine-tuning for robot-friendly scene generation
We propose Nav2Scene, a navigation-driven fine-tuning approach for generating robot-friendly scenes that are optimized for navigation tasks.
$%ms_2022_16$ Bowei Jiang * , Tongyuan Bai * , Peng Zheng, Tieru Wu, Rui Ma #
PDF Cite
Nav2Scene: Navigation-driven fine-tuning for robot-friendly scene generation
3D-SSGAN: Lifting 2D Semantics for 3D-Aware Compositional Portrait Synthesis
Click the Cite button above to demo the feature to enable visitors to import publication metadata into their reference management software. Create your slides in Markdown - click the Slides button to check out the example.
Ruiqi Liu * , Peng Zheng * , Ye Wang, Rui Ma #
PDF Cite
3D-SSGAN: Lifting 2D Semantics for 3D-Aware Compositional Portrait Synthesis
SAC-GAN: Structure-Aware Image Composition
We introduce an end-to-end learning framework for image-to-image composition, aiming to seamlessly compose an object represented as a cropped patch from an object image into a background scene image.
Hang Zhou, Rui Ma # , Lingxiao Zhang, Lin Gao, Ali Mahdavi-Amiri, Hao Zhang
PDF Cite Code
SAC-GAN: Structure-Aware Image Composition
View-Aware Geometry-Structure Joint Learning for Single-View 3D Shape Reconstruction
We introduce VGSNet to jointly learn a multimodal feature representation of 2D image, 3D shape geometry and structure so that both geometry and structure details can be reconstructed from a single-view image.
Xuancheng Zhang * , Rui Ma * , Changqing Zou, Minghao Zhang, Xibin Zhao # , Yue Gao #
PDF Cite
View-Aware Geometry-Structure Joint Learning for Single-View 3D Shape Reconstruction
Organizing Heterogeneous Scene Collection through Contextual Focal Points
We introduce focal points for characterizing, comparing, and organizing collections of complex and heterogeneous data and apply the concepts and algorithms developed to collections of 3D indoor scenes.
Cite Project
Organizing Heterogeneous Scene Collection through Contextual Focal Points
Topology-Varying 3D Shape Creation via Structural Blending
We introduce an algorithm for generating novel 3D models via topology-varying shape blending. Given two shapes with different topology, our method blends them topologically and geometrically, producing continuous series of in-betweens representing new creations.
Cite Project
Topology-Varying 3D Shape Creation via Structural Blending
Language-Driven Synthesis of 3D Scenes from Scene Databases
We introduce a novel framework for using natural language to generate and edit 3D indoor scenes, harnessing scene semantics and text-scene grounding knowledge learned from large annotated 3D scene databases
Cite Project
Language-Driven Synthesis of 3D Scenes from Scene Databases
Action-Driven 3D Indoor Scene Evolution
We introduce a framework for action-driven evolution of 3D indoor scenes, where the goal is to simulate how scenes are altered by human actions, and specifically, by object placements necessitated by the actions.
Cite Project
Action-Driven 3D Indoor Scene Evolution