9 papers · 1 filter
Towards Unified Co-Speech Gesture Generation via Hierarchical Implicit Periodicity Learning
Xin Guo, Yifan Zhao, Jia Li
Generating 3D-based body movements from speech shows great potential in extensive downstream applications, while it still suffers challenges in imitating realistic human movements.…
ChronosObserver: Taming 4D World with Hyperspace Diffusion Sampling
Qisen Wang, Yifan Zhao, Peisen Shen +2
Although prevailing camera-controlled video generation models can produce cinematic results, lifting them directly to the generation of 3D-consistent and high-fidelity time-synchro…
PolarGS: Polarimetric Cues for Ambiguity-Free Gaussian Splatting with Accurate Geometry Recovery
Bo Guo, Sijia Wen, Yifan Zhao +2
Recent advances in surface reconstruction for 3D Gaussian Splatting (3DGS) have enabled remarkable geometric accuracy. However, their performance degrades in photometrically ambigu…
Free Lunch to Meet the Gap: Intermediate Domain Reconstruction for Cross-Domain Few-Shot Learning
Tong Zhang, Yifan Zhao, Liangyu Wang +1
Cross-Domain Few-Shot Learning (CDFSL) endeavors to transfer generalized knowledge from the source domain to target domains using only a minimal amount of training data, which face…
Re-coding for Uncertainties: Edge-awareness Semantic Concordance for Resilient Event-RGB Segmentation
Nan Bao, Yifan Zhao, Lin Zhu +1
Semantic segmentation has achieved great success in ideal conditions. However, when facing extreme conditions (e.g., insufficient light, fierce camera motion), most existing method…
Diffusion-Classifier Synergy: Reward-Aligned Learning via Mutual Boosting Loop for FSCIL
Ruitao Wu, Yifan Zhao, Guangyao Chen +1
Few-Shot Class-Incremental Learning (FSCIL) challenges models to sequentially learn new classes from minimal examples without forgetting prior knowledge, a task complicated by the…
FICGen: Frequency-Inspired Contextual Disentanglement for Layout-driven Degraded Image Generation
Wenzhuang Wang, Yifan Zhao, Mingcan Ma +4
Layout-to-image (L2I) generation has exhibited promising results in natural domains, but suffers from limited generative fidelity and weak alignment with user-provided layouts when…
Learning Yourself: Class-Incremental Semantic Segmentation with Language-Inspired Bootstrapped Disentanglement
Ruitao Wu, Yifan Zhao, Jia Li
Class-Incremental Semantic Segmentation (CISS) requires continuous learning of newly introduced classes while retaining knowledge of past classes. By abstracting mainstream methods…
Provoking Multi-modal Few-Shot LVLM via Exploration-Exploitation In-Context Learning
Cheng Chen, Yunpeng Zhai, Yifan Zhao +3
In-context learning (ICL), a predominant trend in instruction learning, aims at enhancing the performance of large language models by providing clear task guidance and examples, im…