Search Results for author: Guangcong Wang

Found 22 papers, 10 papers with code

Fast Generalizable Gaussian Splatting Reconstruction from Multi-View Stereo

no code implementations20 May 2024 Tianqi Liu, Guangcong Wang, Shoukang Hu, Liao Shen, Xinyi Ye, Yuhang Zang, Zhiguo Cao, Wei Li, Ziwei Liu

We present MVSGaussian, a new generalizable 3D Gaussian representation approach derived from Multi-View Stereo (MVS) that can efficiently reconstruct unseen scenes.

Novel View Synthesis

PERF: Panoramic Neural Radiance Field from a Single Panorama

1 code implementation25 Oct 2023 Guangcong Wang, Peng Wang, Zhaoxi Chen, Wenping Wang, Chen Change Loy, Ziwei Liu

In this paper, we present PERF, a 360-degree novel view synthesis framework that trains a panoramic neural radiance field from a single panorama.

Novel View Synthesis Text to 3D

SparseNeRF: Distilling Depth Ranking for Few-shot Novel View Synthesis

no code implementations ICCV 2023 Guangcong Wang, Zhaoxi Chen, Chen Change Loy, Ziwei Liu

Since coarse depth maps are not strictly scaled to the ground-truth depth maps, we propose a simple yet effective constraint, a local depth ranking method, on NeRFs such that the expected depth ranking of the NeRF is consistent with that of the coarse depth maps in local patches.

Novel View Synthesis

SceneDreamer: Unbounded 3D Scene Generation from 2D Image Collections

1 code implementation2 Feb 2023 Zhaoxi Chen, Guangcong Wang, Ziwei Liu

Our approach begins with an efficient bird's-eye-view (BEV) representation generated from simplex noise, which includes a height field for surface elevation and a semantic field for detailed scene semantics.

Scene Generation

Text2Light: Zero-Shot Text-Driven HDR Panorama Generation

1 code implementation20 Sep 2022 Zhaoxi Chen, Guangcong Wang, Ziwei Liu

To achieve super-resolution inverse tone mapping, we derive a continuous representation of 360-degree imaging from the LDR panorama as a set of structured latent codes anchored to the sphere.

4k inverse tone mapping +3

Understanding Weight Similarity of Neural Networks via Chain Normalization Rule and Hypothesis-Training-Testing

no code implementations8 Aug 2022 Guangcong Wang, Guangrun Wang, Wenqi Liang, JianHuang Lai

We extend the traditional hypothesis-testing method to a hypothesis-training-testing statistical inference method to validate the hypothesis on the weight similarity of neural networks.

Representation Learning

StyleLight: HDR Panorama Generation for Lighting Estimation and Editing

1 code implementation29 Jul 2022 Guangcong Wang, Yinuo Yang, Chen Change Loy, Ziwei Liu

To tackle this problem, we propose a coupled dual-StyleGAN panorama synthesis network (StyleLight) that integrates LDR and HDR panorama synthesis into a unified framework.

Lighting Estimation

Fast-Vid2Vid: Spatial-Temporal Compression for Video-to-Video Synthesis

1 code implementation11 Jul 2022 Long Zhuo, Guangcong Wang, Shikai Li, Wayne Wu, Ziwei Liu

In this paper, we present a spatial-temporal compression framework, \textbf{Fast-Vid2Vid}, which focuses on data aspects of generative models.

Knowledge Distillation Motion Compensation +1

Confidence-guided Adaptive Gate and Dual Differential Enhancement for Video Salient Object Detection

no code implementations14 May 2021 Peijia Chen, JianHuang Lai, Guangcong Wang, Huajun Zhou

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.

object-detection Optical Flow Estimation +2

Solving Inefficiency of Self-supervised Representation Learning

1 code implementation ICCV 2021 Guangrun Wang, Keze Wang, Guangcong Wang, Philip H. S. Torr, Liang Lin

In this paper, we reveal two contradictory phenomena in contrastive learning that we call under-clustering and over-clustering problems, which are major obstacles to learning efficiency.

Clustering Contrastive Learning +4

Joint Learning of Neural Transfer and Architecture Adaptation for Image Recognition

no code implementations31 Mar 2021 Guangrun Wang, Liang Lin, Rongcong Chen, Guangcong Wang, Jiqi Zhang

In this work, we prove that dynamically adapting network architectures tailored for each domain task along with weight finetuning benefits in both efficiency and effectiveness, compared to the existing image recognition pipeline that only tunes the weights regardless of the architecture.

Age Estimation Image Classification +5

Heterogeneous Model Transfer between Different Neural Networks

no code implementations1 Jan 2021 Guangcong Wang, JianHuang Lai, Wenqi Liang, Guangrun Wang

Specifically, we select the longest chain from the source model and transfer it to the longest chain of the target model.

Neural Architecture Search

Smoothing Adversarial Domain Attack and P-Memory Reconsolidation for Cross-Domain Person Re-Identification

no code implementations CVPR 2020 Guangcong Wang, Jian-Huang Lai, Wenqi Liang, Guangrun Wang

To stabilize a memory trace of cross-domain knowledge transfer after its initial acquisition from the source domain, we propose a p-Memory Reconsolidation (pMR) method that reconsolidates the source knowledge with a small probability p during the self-training of the target domain.

Person Re-Identification Transfer Learning

Function Feature Learning of Neural Networks

no code implementations25 Sep 2019 Guangcong Wang, JianHuang Lai, Guangrun Wang, Wenqi Liang

We present a Function Feature Learning (FFL) method that can measure the similarity of non-convex neural networks.

Learnable Parameter Similarity

no code implementations27 Jul 2019 Guangcong Wang, Jian-Huang Lai, Wenqi Liang, Guangrun Wang

Most of the existing approaches focus on specific visual tasks while ignoring the relations between them.

Transfer Learning

Discovering Underlying Person Structure Pattern with Relative Local Distance for Person Re-identification

1 code implementation29 Jan 2019 Guangcong Wang, Jian-Huang Lai, Zhenyu Xie, Xiaohua Xie

With the discovered underlying person structure, the RLD method builds a bridge between the global and local feature representation and thus improves the capacity of feature representation for person re-ID.

Person Re-Identification Representation Learning

Spatial-Temporal Person Re-identification

3 code implementations8 Dec 2018 Guangcong Wang, Jian-Huang Lai, Peigen Huang, Xiaohua Xie

In this paper, we propose a novel two-stream spatial-temporal person ReID (st-ReID) framework that mines both visual semantic information and spatial-temporal information.

Person Re-Identification

Occluded Person Re-identification

no code implementations9 Apr 2018 Jiaxuan Zhuo, Zeyu Chen, Jian-Huang Lai, Guangcong Wang

Person re-identification (re-id) suffers from a serious occlusion problem when applied to crowded public places.

Person Re-Identification

Deep Growing Learning

no code implementations ICCV 2017 Guangcong Wang, Xiaohua Xie, Jian-Huang Lai, Jiaxuan Zhuo

A bottleneck of SSL is the overfitting problem when training over the limited labeled data, especially on a complex model like a deep neural network.

Cannot find the paper you are looking for? You can Submit a new open access paper.