Minglun Gong
YOU?
Author Swipe
View article: Gaussian Set Surface Reconstruction through Per-Gaussian Optimization
Gaussian Set Surface Reconstruction through Per-Gaussian Optimization Open
3D Gaussian Splatting (3DGS) effectively synthesizes novel views through its flexible representation, yet fails to accurately reconstruct scene geometry. While modern variants like PGSR introduce additional losses to ensure proper depth an…
View article: Crystal structure of <i>catena</i> -poly(μ2-6-chloropyridine-2-carboxylato-κ <sup>3</sup> <i>N,O:O</i> ′)(6-chloropyridine-2-carboxylato-κ <sup>2</sup> <i>O,N</i> )copper(II), C <sub>12</sub> H <sub>6</sub> Cl <sub>2</sub> N <sub>2</sub> O <sub>4</sub> Cu
Crystal structure of <i>catena</i> -poly(μ2-6-chloropyridine-2-carboxylato-κ <sup>3</sup> <i>N,O:O</i> ′)(6-chloropyridine-2-carboxylato-κ <sup>2</sup> <i>O,N</i> )copper(II), C <sub>12</sub> H <sub>6</sub> Cl <sub>2</sub> N <sub>2</sub> O <sub>4</sub> Cu Open
C 12 H 6 Cl 2 N 2 O 4 Cu, monoclinic, P 2 1 / c (no. 14), a = 8.3439(5) Å, b = 8.0718(5) Å, c = 20.2384(13) Å, β = 99.650(1)°, V = 1343.78(14) Å 3 , Z = 4, R gt ( F ) = 0.0236, wR ref ( F 2 ) = 0.0633, T = 296 K.
View article: Building LOD Representation for 3D Urban Scenes
Building LOD Representation for 3D Urban Scenes Open
The advances in 3D reconstruction technology, such as photogrammetry and LiDAR scanning, have made it easier to reconstruct accurate and detailed 3D models for urban scenes. Nevertheless, these reconstructed models often contain a large nu…
View article: Real-Time Spatial Reasoning by Mobile Robots for Reconstruction and Navigation in Dynamic LiDAR Scenes
Real-Time Spatial Reasoning by Mobile Robots for Reconstruction and Navigation in Dynamic LiDAR Scenes Open
Our brain has an inner global positioning system which enables us to sense and navigate 3D spaces in real time. Can mobile robots replicate such a biological feat in a dynamic environment? We introduce the first spatial reasoning framework…
View article: ArcPro: Architectural Programs for Structured 3D Abstraction of Sparse Points
ArcPro: Architectural Programs for Structured 3D Abstraction of Sparse Points Open
We introduce ArcPro, a novel learning framework built on architectural programs to recover structured 3D abstractions from highly sparse and low-quality point clouds. Specifically, we design a domain-specific language (DSL) to hierarchical…
View article: Attention-Guided Deep Reinforcement Learning for Realistic Neural Painting
Attention-Guided Deep Reinforcement Learning for Realistic Neural Painting Open
Neural painting aims to produce realistic artworks using stroke sequences, having attracted considerable interest from academia and industry. Previous methods often focus on minimizing the total color distance, neglecting distinctions betw…
View article: ProGen: Revisiting Probabilistic Spatial-Temporal Time Series Forecasting from a Continuous Generative Perspective Using Stochastic Differential Equations
ProGen: Revisiting Probabilistic Spatial-Temporal Time Series Forecasting from a Continuous Generative Perspective Using Stochastic Differential Equations Open
Accurate forecasting of spatiotemporal data remains challenging due to complex spatial dependencies and temporal dynamics. The inherent uncertainty and variability in such data often render deterministic models insufficient, prompting a sh…
View article: Systematic Literature Review of Vision-Based Approaches to Outdoor Livestock Monitoring with Lessons from Wildlife Studies
Systematic Literature Review of Vision-Based Approaches to Outdoor Livestock Monitoring with Lessons from Wildlife Studies Open
Precision livestock farming (PLF) aims to improve the health and welfare of livestock animals and farming outcomes through the use of advanced technologies. Computer vision, combined with recent advances in machine learning and deep learni…
View article: Architectural Co-LOD Generation
Architectural Co-LOD Generation Open
Managing the level-of-detail (LOD) in architectural models is crucial yet challenging, particularly for effective representation and visualization of buildings. Traditional approaches often fail to deliver controllable detail alongside sem…
View article: Textured-GS: Gaussian Splatting with Spatially Defined Color and Opacity
Textured-GS: Gaussian Splatting with Spatially Defined Color and Opacity Open
In this paper, we introduce Textured-GS, an innovative method for rendering Gaussian splatting that incorporates spatially defined color and opacity variations using Spherical Harmonics (SH). This approach enables each Gaussian to exhibit …
View article: SealD-NeRF: Interactive Pixel-Level Editing for Dynamic Scenes by Neural Radiance Fields
SealD-NeRF: Interactive Pixel-Level Editing for Dynamic Scenes by Neural Radiance Fields Open
The widespread adoption of implicit neural representations, especially Neural Radiance Fields (NeRF) as detailed by [1], highlights a growing need for editing capabilities in implicit 3D models, essential for tasks like scene post- process…
View article: SealD-NeRF: Interactive Pixel-Level Editing for Dynamic Scenes by Neural Radiance Fields
SealD-NeRF: Interactive Pixel-Level Editing for Dynamic Scenes by Neural Radiance Fields Open
The widespread adoption of implicit neural representations, especially Neural Radiance Fields (NeRF), highlights a growing need for editing capabilities in implicit 3D models, essential for tasks like scene post-processing and 3D content c…
View article: Enhancing Zero-shot Counting via Language-guided Exemplar Learning
Enhancing Zero-shot Counting via Language-guided Exemplar Learning Open
Recently, Class-Agnostic Counting (CAC) problem has garnered increasing attention owing to its intriguing generality and superior efficiency compared to Category-Specific Counting (CSC). This paper proposes a novel ExpressCount to enhance …
View article: Neural Packing: from Visual Sensing to Reinforcement Learning
Neural Packing: from Visual Sensing to Reinforcement Learning Open
We present a novel learning framework to solve the transport-and-packing (TAP) problem in 3D. It constitutes a full solution pipeline from partial observations of input objects via RGBD sensing and recognition to final box placement, via r…
View article: GRIG: Few-Shot Generative Residual Image Inpainting
GRIG: Few-Shot Generative Residual Image Inpainting Open
Image inpainting is the task of filling in missing or masked region of an image with semantically meaningful contents. Recent methods have shown significant improvement in dealing with large-scale missing regions. However, these methods us…
View article: FER-former: Multi-modal Transformer for Facial Expression Recognition
FER-former: Multi-modal Transformer for Facial Expression Recognition Open
The ever-increasing demands for intuitive interactions in Virtual Reality has triggered a boom in the realm of Facial Expression Recognition (FER). To address the limitations in existing approaches (e.g., narrow receptive fields and homoge…
View article: Visibility-Aware Pixelwise View Selection for Multi-View Stereo Matching
Visibility-Aware Pixelwise View Selection for Multi-View Stereo Matching Open
The performance of PatchMatch-based multi-view stereo algorithms depends heavily on the source views selected for computing matching costs. Instead of modeling the visibility of different views, most existing approaches handle occlusions i…
View article: GCNet: Probing Self-Similarity Learning for Generalized Counting Network
GCNet: Probing Self-Similarity Learning for Generalized Counting Network Open
The class-agnostic counting (CAC) problem has caught increasing attention recently due to its wide societal applications and arduous challenges. To count objects of different categories, existing approaches rely on user-provided exemplars,…
View article: Supplementary Material for: Neuromechanical Dimorphism of Hypoglycemic Effect of Electroacupuncture
Supplementary Material for: Neuromechanical Dimorphism of Hypoglycemic Effect of Electroacupuncture Open
Introduction: Eletroacupuncture (EA) has a favorable impact on blood glucose stability. Blood glucose homeostasis is linked to sexual dimorphism. The majority of research has, however, focused on male participants, and sex differences have…
View article: CrowdMLP: Weakly-Supervised Crowd Counting via Multi-Granularity MLP
CrowdMLP: Weakly-Supervised Crowd Counting via Multi-Granularity MLP Open
Existing state-of-the-art crowd counting algorithms rely excessively on location-level annotations, which are burdensome to acquire. When only count-level (weak) supervisory signals are available, it is arduous and error-prone to regress t…
View article: 3D Pose Estimation and Future Motion Prediction from 2D Images
3D Pose Estimation and Future Motion Prediction from 2D Images Open
This paper considers to jointly tackle the highly correlated tasks of estimating 3D human body poses and predicting future 3D motions from RGB image sequences. Based on Lie algebra pose representation, a novel self-projection mechanism is …
View article: Action2video: Generating Videos of Human 3D Actions
Action2video: Generating Videos of Human 3D Actions Open
We aim to tackle the interesting yet challenging problem of generating videos of diverse and natural human motions from prescribed action categories. The key issue lies in the ability to synthesize multiple distinct motion sequences that a…
View article: EventHPE: Event-based 3D Human Pose and Shape Estimation
EventHPE: Event-based 3D Human Pose and Shape Estimation Open
Event camera is an emerging imaging sensor for capturing dynamics of moving objects as events, which motivates our work in estimating 3D human pose and shape from the event signals. Events, on the other hand, have their unique challenges: …
View article: EventHPE: Event-based 3D Human Pose and Shape Estimation
EventHPE: Event-based 3D Human Pose and Shape Estimation Open
Event camera is an emerging imaging sensor for capturing dynamics of moving objects as events, which motivates our work in estimating 3D human pose and shape from the event signals. Events, on the other hand, have their unique challenges: …
View article: Object Wake-up: 3-D Object Reconstruction, Animation, and in-situ Rendering from a Single Image
Object Wake-up: 3-D Object Reconstruction, Animation, and in-situ Rendering from a Single Image Open
Given a picture of a chair, could we extract the 3-D shape of the chair, animate its plausible articulations and motions, and render in-situ in its original image space? The above question prompts us to devise an automated approach to extr…
View article: Object Wake-up: 3D Object Rigging from a Single Image
Object Wake-up: 3D Object Rigging from a Single Image Open
Given a single image of a general object such as a chair, could we also restore its articulated 3D shape similar to human modeling, so as to animate its plausible articulations and diverse motions? This is an interesting new question that …
View article: Unsupervised 3D Human Mesh Recovery from Noisy Point Clouds.
Unsupervised 3D Human Mesh Recovery from Noisy Point Clouds. Open
This paper presents a novel unsupervised approach to reconstruct human shape and pose from noisy point cloud. Traditional approaches search for correspondences and conduct model fitting iteratively where a good initialization is critical. …