43 citations · 134 across the 22 of their papers we have counts for
22 papers
EvTrajGS: Accurate and Efficient 3D Gaussian Splatting from Unposed Event Streams
Zixuan Chen, Jiakai Zhang, Junhao Dong +4
Event cameras, with high temporal resolution, high dynamic range, and asynchronous sensing characteristics, have shown great potential for dense 3D reconstruction. Traditional reco…
SegmentDreamer: Towards High-fidelity Text-to-3D Synthesis with Segmented Consistency Trajectory Distillation
Jiahao Zhu, Zixuan Chen, Guangcong Wang +2
Recent advancements in text-to-3D generation improve the visual quality of Score Distillation Sampling (SDS) and its variants by directly connecting Consistency Distillation (CD) t…
DiffV2IR: Visible-to-Infrared Diffusion Model via Vision-Language Understanding
Lingyan Ran, Lidong Wang, Guangcong Wang +2
The task of translating visible-to-infrared images (V2IR) is inherently challenging due to three main obstacles: 1) achieving semantic-aware translation, 2) managing the diverse wa…
GuardSplat: Efficient and Robust Watermarking for 3D Gaussian Splatting
Zixuan Chen, Guangcong Wang, Jiahao Zhu +2
3D Gaussian Splatting (3DGS) has recently created impressive 3D assets for various applications. However, considering security, capacity, invisibility, and training efficiency, the…
MVSGaussian: Fast Generalizable Gaussian Splatting Reconstruction from Multi-View Stereo
Tianqi Liu, Guangcong Wang, Shoukang Hu +6
We present MVSGaussian, a new generalizable 3D Gaussian representation approach derived from Multi-View Stereo (MVS) that can efficiently reconstruct unseen scenes. Specifically, 1…
PrimDiffusion: Volumetric Primitives Diffusion for 3D Human Generation
Zhaoxi Chen, Fangzhou Hong, Haiyi Mei +3
We present PrimDiffusion, the first diffusion-based framework for 3D human generation. Devising diffusion models for 3D human generation is difficult due to the intensive computati…
PERF: Panoramic Neural Radiance Field from a Single Panorama
Guangcong Wang, Peng Wang, Zhaoxi Chen +3
Neural Radiance Field (NeRF) has achieved substantial progress in novel view synthesis given multi-view images. Recently, some works have attempted to train a NeRF from a single im…
SparseNeRF: Distilling Depth Ranking for Few-shot Novel View Synthesis
Guangcong Wang, Zhaoxi Chen, Chen Change Loy +1
Neural Radiance Field (NeRF) significantly degrades when only a limited number of views are available. To complement the lack of 3D information, depth-based models, such as DSNeRF…
SceneDreamer: Unbounded 3D Scene Generation from 2D Image Collections
Zhaoxi Chen, Guangcong Wang, Ziwei Liu
In this work, we present SceneDreamer, an unconditional generative model for unbounded 3D scenes, which synthesizes large-scale 3D landscapes from random noise. Our framework is le…
Text2Light: Zero-Shot Text-Driven HDR Panorama Generation
Zhaoxi Chen, Guangcong Wang, Ziwei Liu
High-quality HDRIs(High Dynamic Range Images), typically HDR panoramas, are one of the most popular ways to create photorealistic lighting and 360-degree reflections of 3D scenes i…
Understanding Weight Similarity of Neural Networks via Chain Normalization Rule and Hypothesis-Training-Testing
Guangcong Wang, Guangrun Wang, Wenqi Liang +1
We present a weight similarity measure method that can quantify the weight similarity of non-convex neural networks. To understand the weight similarity of different trained models…
StyleLight: HDR Panorama Generation for Lighting Estimation and Editing
Guangcong Wang, Yinuo Yang, Chen Change Loy +1
We present a new lighting estimation and editing framework to generate high-dynamic-range (HDR) indoor panorama lighting from a single limited field-of-view (LFOV) image captured b…
Fast-Vid2Vid: Spatial-Temporal Compression for Video-to-Video Synthesis
Long Zhuo, Guangcong Wang, Shikai Li +2
Video-to-Video synthesis (Vid2Vid) has achieved remarkable results in generating a photo-realistic video from a sequence of semantic maps. However, this pipeline suffers from high…
Confidence-guided Adaptive Gate and Dual Differential Enhancement for Video Salient Object Detection
Peijia Chen, Jianhuang Lai, Guangcong Wang +1
Video salient object detection (VSOD) aims to locate and segment the most attractive object by exploiting both spatial cues and temporal cues hidden in video sequences. However, sp…
Solving Inefficiency of Self-supervised Representation Learning
Guangrun Wang, Keze Wang, Guangcong Wang +2
Self-supervised learning (especially contrastive learning) has attracted great interest due to its huge potential in learning discriminative representations in an unsupervised mann…
Joint Learning of Neural Transfer and Architecture Adaptation for Image Recognition
Guangrun Wang, Liang Lin, Rongcong Chen +2
Current state-of-the-art visual recognition systems usually rely on the following pipeline: (a) pretraining a neural network on a large-scale dataset (e.g., ImageNet) and (b) finet…
Learnable Parameter Similarity
Guangcong Wang, Jianhuang Lai, Wenqi Liang +1
Most of the existing approaches focus on specific visual tasks while ignoring the relations between them. Estimating task relation sheds light on the learning of high-order semanti…
Weakly Supervised Person Re-ID: Differentiable Graphical Learning and A New Benchmark
Guangrun Wang, Guangcong Wang, Xujie Zhang +3
Person re-identification (Re-ID) benefits greatly from the accurate annotations of existing datasets (e.g., CUHK03 [1] and Market-1501 [2]), which are quite expensive because each…
Discovering Underlying Person Structure Pattern with Relative Local Distance for Person Re-identification
Guangcong Wang, Jianhuang Lai, Zhenyu Xie +1
Modeling the underlying person structure for person re-identification (re-ID) is difficult due to diverse deformable poses, changeable camera views and imperfect person detectors.…
Spatial-Temporal Person Re-identification
Guangcong Wang, Jianhuang Lai, Peigen Huang +1
Most of current person re-identification (ReID) methods neglect a spatial-temporal constraint. Given a query image, conventional methods compute the feature distances between the q…
M2M-GAN: Many-to-Many Generative Adversarial Transfer Learning for Person Re-Identification
Wenqi Liang, Guangcong Wang, Jianhuang Lai +1
Cross-domain transfer learning (CDTL) is an extremely challenging task for the person re-identification (ReID). Given a source domain with annotations and a target domain without a…
Occluded Person Re-identification
Jiaxuan Zhuo, Zeyu Chen, Jianhuang Lai +1
Person re-identification (re-id) suffers from a serious occlusion problem when applied to crowded public places. In this paper, we propose to retrieve a full-body person image by u…