69 citations · 118 across the 14 of their papers we have counts for
14 papers · 1 filter
Degradation Frequency Curve: An Explicit Frequency-Quantified Representation for All-in-One Image Restoration
Xinghua Huang, Zhixiong Yang, Chen Wu +6
A fundamental difficulty in all-in-one blind image restoration is that degradation is usually treated as an implicit factor hidden in degraded-to-clean mapping, rather than as an e…
Gaussian-Voxel Duet: A Dual-Scaffolding Hybrid Representation for Fast and Accurate Monocular Surface Reconstruction
Zhenhua Du, Zhen Tan, Haoyu Zhang +3
While 3D Gaussian Splatting has achieved remarkable success in photorealistic novel view synthesis, its pursuit of fast and high-fidelity 3D reconstruction has long been constraine…
Step-wise Distribution Alignment Guided Style Prompt Tuning for Source-free Cross-domain Few-shot Learning
Huali Xu, Li Liu, Tianpeng Liu +3
Existing cross-domain few-shot learning (CDFSL) methods, which develop source-domain training strategies to enhance model transferability, face challenges with large-scale pre-trai…
Enhancing Information Maximization with Distance-Aware Contrastive Learning for Source-Free Cross-Domain Few-Shot Learning
Huali Xu, Li Liu, Shuaifeng Zhi +4
Existing Cross-Domain Few-Shot Learning (CDFSL) methods require access to source domain data to train a model in the pre-training phase. However, due to increasing concerns about d…
ROFusion: Efficient Object Detection using Hybrid Point-wise Radar-Optical Fusion
Liu Liu, Shuaifeng Zhi, Zhenhua Du +4
Radars, due to their robustness to adverse weather conditions and ability to measure object motions, have served in autonomous driving and intelligent agents for years. However, Ra…
Unbiased Scene Graph Generation via Two-stage Causal Modeling
Shuzhou Sun, Shuaifeng Zhi, Qing Liao +2
Despite the impressive performance of recent unbiased Scene Graph Generation (SGG) methods, the current debiasing literature mainly focuses on the long-tailed distribution problem,…
PlaneRecTR++: Unified Query Learning for Joint 3D Planar Reconstruction and Pose Estimation
Jingjia Shi, Shuaifeng Zhi, Kai Xu
The challenging task of 3D planar reconstruction from images involves several sub-tasks including frame-wise plane detection, segmentation, parameter regression and possibly depth…
Deep Learning for Cross-Domain Few-Shot Visual Recognition: A Survey
Huali Xu, Shuaifeng Zhi, Shuzhou Sun +2
While deep learning excels in computer vision tasks with abundant labeled data, its performance diminishes significantly in scenarios with limited labeled samples. To address this,…
SSR-2D: Semantic 3D Scene Reconstruction from 2D Images
Junwen Huang, Alexey Artemov, Yujin Chen +3
Most deep learning approaches to comprehensive semantic modeling of 3D indoor spaces require costly dense annotations in the 3D domain. In this work, we explore a central 3D scene…
Cross-Domain Few-Shot Classification via Inter-Source Stylization
Huali Xu, Shuaifeng Zhi, Li Liu
The goal of Cross-Domain Few-Shot Classification (CDFSC) is to accurately classify a target dataset with limited labelled data by exploiting the knowledge of a richly labelled auxi…
ILabel: Interactive Neural Scene Labelling
Shuaifeng Zhi, Edgar Sucar, Andre Mouton +3
Joint representation of geometry, colour and semantics using a 3D neural field enables accurate dense labelling from ultra-sparse interactions as a user reconstructs a scene in rea…
Bootstrapping Semantic Segmentation with Regional Contrast
Shikun Liu, Shuaifeng Zhi, Edward Johns +1
We present ReCo, a contrastive learning framework designed at a regional level to assist learning in semantic segmentation. ReCo performs semi-supervised or supervised pixel-level…
In-Place Scene Labelling and Understanding with Implicit Scene Representation
Shuaifeng Zhi, Tristan Laidlow, Stefan Leutenegger +1
Semantic labelling is highly correlated with geometry and radiance reconstruction, as scene entities with similar shape and appearance are more likely to come from similar classes.…
SceneCode: Monocular Dense Semantic Reconstruction using Learned Encoded Scene Representations
Shuaifeng Zhi, Michael Bloesch, Stefan Leutenegger +1
Systems which incrementally create 3D semantic maps from image sequences must store and update representations of both geometry and semantic entities. However, while there has been…