27 citations · 81 across the 20 of their papers we have counts for
21 papers
TempAct: Advancing Temporal Plausibility in Autoregressive Video Generation via Planner-Executor RL
Jing Wang, Xiangxin Zhou, Jiajun Liang +5
Autoregressive (AR) video diffusion models enable low-latency streaming generation by synthesizing videos chunk by chunk with cached visual context, but this chunk-wise formulation…
HairOrbit: Multi-view Aware 3D Hair Modeling from Single Portraits
Leyang Jin, Yujian Zheng, Bingkui Tong +3
Reconstructing strand-level 3D hair from a single-view image is highly challenging, especially when preserving consistent and realistic attributes in unseen regions. Existing metho…
AnyCrowd: Instance-Isolated Identity-Pose Binding for Arbitrary Multi-Character Animation
Zhenyu Xie, Ji Xia, Michael Kampffmeyer +9
Controllable character animation has advanced rapidly in recent years, yet multi-character animation remains underexplored. As the number of characters grows, multi-character refer…
Steering Video Diffusion Transformers with Massive Activations
Xianhang Cheng, Yujian Zheng, Zhenyu Xie +2
In this work, we study the role of Massive Activations (MAs), which are rare, high-magnitude spikes confined to a few fixed hidden dimensions in video diffusion transformers (DiTs)…
ERGO: Excess-Risk-Guided Optimization for High-Fidelity Monocular 3D Gaussian Splatting
Zehua Ma, Hanhui Li, Zhenyu Xie +4
Generating 3D content from a single image remains a fundamentally challenging and ill-posed problem due to the inherent absence of geometric and textural information in occluded re…
GRPO-Guard: Mitigating Implicit Over-Optimization in Flow Matching via Regulated Clipping
Jing Wang, Jiajun Liang, Jie Liu +10
Recently, GRPO-based reinforcement learning has shown remarkable progress in optimizing flow-matching models, effectively improving their alignment with task-specific rewards. With…
DreamVTON: Customizing 3D Virtual Try-on with Personalized Diffusion Models
Zhenyu Xie, Haoye Dong, Yufei Gao +2
Image-based 3D Virtual Try-ON (VTON) aims to sculpt the 3D human according to person and clothes images, which is data-efficient (i.e., getting rid of expensive 3D data) but challe…
MMTryon: Multi-Modal Multi-Reference Control for High-Quality Fashion Generation
Xujie Zhang, Ente Lin, Michael Kampffmeyer +6
This paper introduces MMTryon, a multi-modal multi-reference VIrtual Try-ON (VITON) framework, which can generate high-quality compositional try-on results by taking a text instruc…
Towards Detailed Text-to-Motion Synthesis via Basic-to-Advanced Hierarchical Diffusion Model
Zhenyu Xie, Yang Wu, Xuehao Gao +3
Text-guided motion synthesis aims to generate 3D human motion that not only precisely reflects the textual description but reveals the motion details as much as possible. Pioneerin…
WarpDiffusion: Efficient Diffusion Model for High-Fidelity Virtual Try-on
xujie zhang, Xiu Li, Michael Kampffmeyer +5
Image-based Virtual Try-On (VITON) aims to transfer an in-shop garment image onto a target person. While existing methods focus on warping the garment to fit the body pose, they of…
Fashion Matrix: Editing Photos by Just Talking
Zheng Chong, Xujie Zhang, Fuwei Zhao +2
The utilization of Large Language Models (LLMs) for the construction of AI systems has garnered significant attention across diverse fields. The extension of LLMs to the domain of…
Towards Hard-pose Virtual Try-on via 3D-aware Global Correspondence Learning
Zaiyu Huang, Hanhui Li, Zhenyu Xie +3
In this paper, we target image-based person-to-person virtual try-on in the presence of diverse poses and large viewpoint variations. Existing methods are restricted in this settin…
ARMANI: Part-level Garment-Text Alignment for Unified Cross-Modal Fashion Design
Xujie Zhang, Yu Sha, Michael C. Kampffmeyer +5
Cross-modal fashion image synthesis has emerged as one of the most promising directions in the generation domain due to the vast untapped potential of incorporating multiple modali…
PASTA-GAN++: A Versatile Framework for High-Resolution Unpaired Virtual Try-on
Zhenyu Xie, Zaiyu Huang, Fuwei Zhao +5
Image-based virtual try-on is one of the most promising applications of human-centric image generation due to its tremendous real-world potential. In this work, we take a step forw…
Dressing in the Wild by Watching Dance Videos
Xin Dong, Fuwei Zhao, Zhenyu Xie +6
While significant progress has been made in garment transfer, one of the most applicable directions of human-centric image generation, existing works overlook the in-the-wild image…
Towards Scalable Unpaired Virtual Try-On via Patch-Routed Spatially-Adaptive GAN
Zhenyu Xie, Zaiyu Huang, Fuwei Zhao +3
Image-based virtual try-on is one of the most promising applications of human-centric image generation due to its tremendous real-world potential. Yet, as most try-on approaches fi…
Image Comes Dancing with Collaborative Parsing-Flow Video Synthesis
Bowen Wu, Zhenyu Xie, Xiaodan Liang +3
Transferring human motion from a source to a target person poses great potential in computer vision and graphics applications. A crucial step is to manipulate sequential future mot…
M3D-VTON: A Monocular-to-3D Virtual Try-On Network
Fuwei Zhao, Zhenyu Xie, Michael Kampffmeyer +5
Virtual 3D try-on can provide an intuitive and realistic view for online shopping and has a huge potential commercial value. However, existing 3D virtual try-on methods mainly rely…
WAS-VTON: Warping Architecture Search for Virtual Try-on Network
Zhenyu Xie, Xujie Zhang, Fuwei Zhao +4
Despite recent progress on image-based virtual try-on, current methods are constraint by shared warping networks and thus fail to synthesize natural try-on results when faced with…
Fashion Editing with Adversarial Parsing Learning
Haoye Dong, Xiaodan Liang, Yixuan Zhang +6
Interactive fashion image manipulation, which enables users to edit images with sketches and color strokes, is an interesting research problem with great application value. Existin…
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.…