Manyi Li
YOU?
Author Swipe
View article: AG$^2$aussian: Anchor-Graph Structured Gaussian Splatting for Instance-Level 3D Scene Understanding and Editing
AG$^2$aussian: Anchor-Graph Structured Gaussian Splatting for Instance-Level 3D Scene Understanding and Editing Open
3D Gaussian Splatting (3DGS) has witnessed exponential adoption across diverse applications, driving a critical need for semantic-aware 3D Gaussian representations to enable scene understanding and editing tasks. Existing approaches typica…
View article: Pay Less Attention to Deceptive Artifacts: Robust Detection of Compressed Deepfakes on Online Social Networks
Pay Less Attention to Deceptive Artifacts: Robust Detection of Compressed Deepfakes on Online Social Networks Open
With the rapid advancement of deep learning, particularly through generative adversarial networks (GANs) and diffusion models (DMs), AI-generated images, or ``deepfakes", have become nearly indistinguishable from real ones. These images ar…
View article: FreeScene: Mixed Graph Diffusion for 3D Scene Synthesis from Free Prompts
FreeScene: Mixed Graph Diffusion for 3D Scene Synthesis from Free Prompts Open
Controllability plays a crucial role in the practical applications of 3D indoor scene synthesis. Existing works either allow rough language-based control, that is convenient but lacks fine-grained scene customization, or employ graph based…
View article: Adaptive and Iterative Point Cloud Denoising with Score‐Based Diffusion Model
Adaptive and Iterative Point Cloud Denoising with Score‐Based Diffusion Model Open
Point cloud denoising task aims to recover the clean point cloud from the scanned data coupled with different levels or patterns of noise. The recent state‐of‐the‐art methods often train deep neural networks to update the point locations t…
View article: SymBridge: A Human-in-the-Loop Cyber-Physical Interactive System for Adaptive Human-Robot Symbiosis
SymBridge: A Human-in-the-Loop Cyber-Physical Interactive System for Adaptive Human-Robot Symbiosis Open
The development of intelligent robots seeks to seamlessly integrate them into the human world, providing assistance and companionship in daily life and work, with the ultimate goal of achieving human-robot symbiosis. This requires robots w…
View article: Unit Region Encoding: A Unified and Compact Geometry-aware Representation for Floorplan Applications
Unit Region Encoding: A Unified and Compact Geometry-aware Representation for Floorplan Applications Open
We present the Unit Region Encoding of floorplans, which is a unified and compact geometry-aware encoding representation for various applications, ranging from interior space planning, floorplan metric learning to floorplan generation task…
View article: Sequential selection and calibration of video frames for 3D outdoor scene reconstruction
Sequential selection and calibration of video frames for 3D outdoor scene reconstruction Open
3D scene understanding and reconstruction aims to obtain a concise scene representation from images and reconstruct the complete scene, including the scene layout, objects bounding boxes and shapes. Existing holistic scene understanding me…
View article: Influence of Land Use Types on Soil Properties and Soil Quality in Karst Regions of Southwest China
Influence of Land Use Types on Soil Properties and Soil Quality in Karst Regions of Southwest China Open
Establishing a suitable and useful soil quality index (SQI) is the key to accurately evaluating changes in soil quality (SQ) under different land use types. In the present study, a suitable and useful SQI using a minimum data set (MDS) wit…
View article: Understanding institutional and policy challenges in China’s coal transition: Insights from the case of Chongqing
Understanding institutional and policy challenges in China’s coal transition: Insights from the case of Chongqing Open
China’s efforts and decisions to phase out coal will shape global endeavors in addressing climate change in the upcoming decades. This study investigates the action logic and interactions among different stakeholders, including the central…
View article: Learning based 2D Irregular Shape Packing
Learning based 2D Irregular Shape Packing Open
2D irregular shape packing is a necessary step to arrange UV patches of a 3D model within a texture atlas for memory-efficient appearance rendering in computer graphics. Being a joint, combinatorial decision-making problem involving all pa…
View article: AffordPose: A Large-scale Dataset of Hand-Object Interactions with Affordance-driven Hand Pose
AffordPose: A Large-scale Dataset of Hand-Object Interactions with Affordance-driven Hand Pose Open
How human interact with objects depends on the functional roles of the target objects, which introduces the problem of affordance-aware hand-object interaction. It requires a large number of human demonstrations for the learning and unders…
View article: Advances in Data‐Driven Analysis and Synthesis of 3D Indoor Scenes
Advances in Data‐Driven Analysis and Synthesis of 3D Indoor Scenes Open
This report surveys advances in deep learning‐based modelling techniques that address four different 3D indoor scene analysis tasks, as well as synthesis of 3D indoor scenes. We describe different kinds of representations for indoor scenes…
View article: Understanding institutional and policy challenges in China’s coal transition: Insights from the case of Chongqing
Understanding institutional and policy challenges in China’s coal transition: Insights from the case of Chongqing Open
China’s efforts and decisions to phase out coal will shape global endeavors in addressing climate change in the upcoming decades. This study investigates the action logic and interactions among different stakeholders, including the central…
View article: Advances in Data-Driven Analysis and Synthesis of 3D Indoor Scenes
Advances in Data-Driven Analysis and Synthesis of 3D Indoor Scenes Open
This report surveys advances in deep learning-based modeling techniques that address four different 3D indoor scene analysis tasks, as well as synthesis of 3D indoor scenes. We describe different kinds of representations for indoor scenes,…
View article: Let's all dance: Enhancing amateur dance motions
Let's all dance: Enhancing amateur dance motions Open
Professional dance is characterized by high impulsiveness, elegance, and aesthetic beauty. In order to reach the desired professionalism, it requires years of long and exhausting practice, good physical condition, musicality, but also, a g…
View article: RIM-Net: Recursive Implicit Fields for Unsupervised Learning of Hierarchical Shape Structures
RIM-Net: Recursive Implicit Fields for Unsupervised Learning of Hierarchical Shape Structures Open
We introduce RIM-Net, a neural network which learns recursive implicit fields for unsupervised inference of hierarchical shape structures. Our network recursively decomposes an input 3D shape into two parts, resulting in a binary tree hier…
View article: CAPRI-Net: Learning Compact CAD Shapes with Adaptive Primitive Assembly
CAPRI-Net: Learning Compact CAD Shapes with Adaptive Primitive Assembly Open
We introduce CAPRI-Net, a neural network for learning compact and interpretable implicit representations of 3D computer-aided design (CAD) models, in the form of adaptive primitive assemblies. Our network takes an input 3D shape that can b…
View article: LayoutGMN: Neural Graph Matching for Structural Layout Similarity
LayoutGMN: Neural Graph Matching for Structural Layout Similarity Open
We present a deep neural network to predict structural similarity between 2D layouts by leveraging Graph Matching Networks (GMN). Our network, coined LayoutGMN, learns the layout metric via neural graph matching, using an attention-based G…
View article: D$^2$IM-Net: Learning Detail Disentangled Implicit Fields from Single Images
D$^2$IM-Net: Learning Detail Disentangled Implicit Fields from Single Images Open
We present the first single-view 3D reconstruction network aimed at recovering geometric details from an input image which encompass both topological shape structures and surface features. Our key idea is to train the network to learn a de…
View article: Language-driven synthesis of 3D scenes from scene databases
Language-driven synthesis of 3D scenes from scene databases Open
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. The advantage of natural langua…
View article: GRAINS: Generative Recursive Autoencoders for INdoor Scenes
GRAINS: Generative Recursive Autoencoders for INdoor Scenes Open
We present a generative neural network which enables us to generate plausible 3D indoor scenes in large quantities and varieties, easily and highly efficiently. Our key observation is that indoor scene structures are inherently hierarchica…