Binbin Huang

Binbin Huang

Auto-generated profile, based on publicly available information

Binbin Huang

University of Hong Kong, Hong Kong SAR, China

Research Focus & Metrics

Academic Career Length

3Years (2024-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
13 July 2024
Verified
Conference Paper
Open access
BHBinbin Huang
Binbin Huang
ZYZehao Yu
Zehao Yu
ACAnpei Chen
Anpei Chen
AGAndreas Geiger
Andreas Geiger
SGShenghua Gao
Shenghua Gao
3D Gaussian Splatting (3DGS) has recently revolutionized radiance field reconstruction, achieving high quality novel view synthesis and fast rendering speed. However, 3DGS fails to accurately represent surfaces due to the multi-view inconsistent nature of 3D Gaussians. We present 2D Gaussian Splatting (2DGS), a novel approach to model and reconstruct geometrically accurate radiance fields from multi-view images. Our key idea is to collapse the 3D volume into a set of 2D oriented planar Gaussian disks. Unlike 3D Gaussians, 2D Gaussians provide view-consistent geometry while modeling surfaces intrinsically. To accurately recover thin surfaces and achieve stable optimization, we introduce a perspective-accurate 2D splatting process utilizing ray-splat intersection and rasterization. Additionally, we incorporate depth distortion and normal consistency terms to further enhance the quality of the reconstructions. We demonstrate that our differentiable renderer allows for noise-free and detailed geometry reconstruction while maintaining competitive appearance quality, fast training speed, and real-time rendering. Project page at https://surfsplatting.github.io.

14 August 2025 in IEEE Transactions on Pattern Analysis and Machine Intelligence
Verified
Journal Article
Closed access
YZYiqun Zhao
Yiqun Zhao
CWChenming Wu
Chenming Wu
BHBinbin Huang
Binbin Huang
YZYihao Zhi
Yihao Zhi
CZChen Zhao
Chen Zhao
SGShenghua Gao
Shenghua Gao
Efficient and accurate reconstruction of a relightable, dynamic clothed human avatar from a monocular video is crucial for the entertainment industry. This article presents SGIA (Surfel-based Gaussian Inverse Avatar), which introduces efficient training and rendering for relightable dynamic human reconstruction. SGIA advances previous Gaussian Avatar methods by comprehensively modeling Physically-Based Rendering (PBR) properties for clothed human avatars, allowing for the manipulation of avatars into novel poses under diverse lighting conditions. Specifically, our approach integrates pre-integration and image-based lighting for fast light calculations that surpass the performance of existing implicit-based techniques. To address challenges related to material lighting disentanglement and accurate geometry reconstruction, we propose an innovative occlusion approximation strategy and a progressive training approach. Extensive experiments demonstrate that SGIA not only achieves highly accurate physical properties but also significantly enhances the realistic relighting of dynamic human avatars, providing a substantial speed advantage.

28 October 2024
Verified
Conference Paper
Open access
JYJinpeng Yu
Jinpeng Yu
BHBinbin Huang
Binbin Huang
YZYuxuan Zhang
Yuxuan Zhang
HLHuaxia Li
Huaxia Li
XTXu Tang
Xu Tang
SGShenghua Gao
Shenghua Gao
Point cloud completion aims to recover accurate global geometry and preserve fine-grained local details from partial point clouds. Conventional methods typically predict unseen points directly from 3D point cloud coordinates or use self-projected multi-view depth maps to ease this task. However, these gray-scale depth maps cannot reach multi-view consistency, consequently restricting the performance. In this paper, we introduce a GeoFormer that simultaneously enhances the global geometric structure of the points and improves the local details. Specifically, we design a CCM Feature Enhanced Point Generator to integrate image features from multi-view consistent canonical coordinate maps (CCMs) and align them with pure point features, thereby enhancing the global geometry feature. Additionally, we employ the Multi-scale Geometry-aware Upsampler module to progressively enhance local details. This is achieved through cross attention between the multi-scale features extracted from the partial input and the features derived from previously estimated points. Extensive experiments on the PCN, ShapeNet-55/34, and KITTI benchmarks demonstrate that our GeoFormer outperforms recent methods, achieving the state-of-the-art performance. Our code is available at https://github.com/Jinpeng-Yu/GeoFormer.

28 October 2024
Verified
Conference Paper
Open access
SLShiyu Liu
Shiyu Liu
ZZZibo Zhao
Zibo Zhao
YZYihao Zhi
Yihao Zhi
YZYiqun Zhao
Yiqun Zhao
BHBinbin Huang
Binbin Huang
SGShenghua Gao
Shenghua Gao
Video generation and editing, particularly human-centric video editing, has seen a surge of interest in its potential to create immersive and dynamic content. A fundamental challenge is ensuring temporal coherence and visual harmony across frames, especially in handling large-scale human motion and maintaining consistency over long sequences. The previous methods, such as zero-shot text-to-video methods with diffusion model, struggle with flickering and length limitations. In contrast, methods employing Video-2D representations grapple with accurately capturing complex structural relationships in large-scale human motion. Simultaneously, some patterns on the human body appear intermittently throughout the video, posing a knotty problem in identifying visual correspondence. To address the above problems, we present HeroMaker. This human-centric video editing framework manipulates the person's appearance within the input video and achieves consistent results across frames. Specifically, we propose to learn the motion priors, which represent the correspondences between dual canonical fields and each video frame, by leveraging the body mesh-based human motion warping and neural deformation-based margin refinement in the video reconstruction framework to ensure the semantic correctness of canonical fields. HeroMaker performs human-centric video editing by manipulating the dual canonical fields and combining them with motion priors to synthesize temporally coherent and visually plausible results. Comprehensive experiments demonstrate that our approach surpasses existing methods regarding temporal consistency, visual quality, and semantic coherence.