207 citations · 2.2k across the 179 of their papers we have counts for
189 papers
HairFlow: Modeling 3D Hair Strands with Multi-Modal Conditioned Diffusion
Yating Wang, Kui Wu, Ran Yi +5
Modeling 3D hair strands is challenging due to complex hairstyle geometry, scarce high-quality training data, and incomplete or noisy input observations. Foundation models offer br…
GraLoD: Graphics-Inspired Continuous Level-of-Detail Learning for Image Restoration
Hu Gao, Lizhuang Ma, Yulong Chen
The spatial support required for image restoration varies across degradation types, image regions, and reconstruction stages. However, most existing methods rely on predefined mult…
Learning to Restore More: Continual Capability Expansion for Pretrained Image Restoration Models
Hu Gao, Yulong Chen, Lizhuang Ma
Image restoration models are typically trained with a fixed set of capabilities. When new restoration requirements emerge, existing solutions usually train additional models or joi…
GroupForward: Building Referable 3D Scenes via Instance-Grouped Feed-Forward Gaussian Splatting
Qijian Tian, Zimeng Wu, Xuhong Wang +2
Simultaneously reconstructing and understanding 3D environments is essential for embodied agents. Toward this goal, feed-forward semantic 3D Gaussian Splatting (3DGS) efficiently c…
TRACE-Bench: Decomposing and Diagnosing Multi-Reference Image Generation
Haoran Wang, Chaofan Ma, Ran Yi +1
Despite recent advances in unified multimodal models for multi-reference image generation, existing benchmarks remain organized around predefined task types (e.g., "subject composi…
VicEdit: Learning to Edit Videos from Visual In-Context Examples
Yuji Wang, Teng Hu, Yuheng Chen +6
Despite remarkable progress in instruction-based video editing, textual descriptions remain limited in expressing fine-grained appearance, spatial transformations, and temporal dyn…
PersonaShot: Benchmarking Person-Centric Narrative Continuity in Multi-Shot Video Generation
Yuji Wang, Yuheng Chen, Teng Hu +7
Video generation is rapidly evolving from single-shot clips to multi-shot narratives, where the human character serves as the core narrative anchor. However, existing benchmarks ma…
Spatial Temporal Synergy: Balancing Change and Invariance in Text Driven 3D Human Motion Editing
Shaohui Lin, Zhenwu Shi, Jingyu Gong +5
Text-driven human motion editing aims to modify existing motion sequences according to natural language instructions while maintaining the structural consistency of the original mo…
Tired Actor: Fatigue-Informed Character Control
Shengyuan Zhang, Xinpeng Liu, Muchun Niu +5
Replicating human behavior with physics simulation has been a long-expected goal in character animation. Existing efforts have achieved impressive performance in imitating a wide s…
Causal-AgentIR: Self-Evolving Causal Memory for Adaptive Image Restoration Agents
Hu Gao, Yulong Chen, Lizhuang Ma
Image restoration agents have recently emerged as a flexible paradigm for handling diverse and unpredictable degradations in real-world scenarios. Existing agents typically formula…
Cycle-World: Mitigating Error Accumulation in Long-term Video World Models via Reverse-Prediction Cycle Consistency
Zihan Su, Teng Hu, Jiangning Zhang +4
Autoregressive diffusion models have enabled high-quality video generation, yet their sequential nature inherently suffers from error accumulation. In long-horizon video synthesis,…
Learning Adaptive Dynamical Features via Multi- Liquid-Mamba for All-in-one Image Restoration
Hu Gao, Changshuo Wang, Yulong Chen +1
Image restoration aims to recover high-quality images from degraded observations. Recent Mamba-based image restoration models have demonstrated strong potential in modeling long-ra…
CineDance: Towards Next-Generation Multi-Shot Long-Form Cinematic Audio-Video Generation
Yuheng Chen, Teng Hu, Yuji Wang +7
The fidelity and structural diversity of training datasets fundamentally determine the capabilities of video generation models. While commercial systems showremarkableabilitytogene…
MetaWorld: Scaling Multi-Agent Video World Model from Single-view Video Data
Teng Hu, Mingchun Lu, Yating Wang +6
Video world models are a foundational generative technology for embodied AI and the Metaverse, yet existing approaches are inherently limited to a single agent observing from a sin…
Spatial-Temporal Decoupled Reference Conditioning for Identity-Preserving Text-to-Video Generation
Yuheng Chen, Teng Hu, Yuji Wang +3
Identity-preserving video generation (IPVG) aims to synthesize high-fidelity videos that follow text prompts while faithfully preserving a reference identity. Despite recent progre…
Omni-Supervised Motion Editing: Balancing Change and Invariance through Positive-Negative Learning
Zhenwu Shi, Jingyu Gong, Peiwei Wang +7
Text-based human motion editing aims to modify existing motion sequences according to natural language instructions while maintaining the consistency of the original motion. Existi…
GSCompleter: A Distillation-Free Plugin for Metric-Aware 3D Gaussian Splatting Completion in Seconds
Ao Gao, Jingyu Gong, Xin Tan +3
3D Gaussian Splatting (3DGS) has revolutionized high-fidelity neural rendering with its explicit representation and efficiency. However, reconstructing scenes from sparse viewpoint…
Omni-Customizer: End-to-End MultiModal Customization for Joint Audio-Video Generation
Yuheng Chen, Qingdong He, Teng Hu +4
The landscape of joint audio and video generation has been fundamentally transformed by the advent of powerful foundation models. Despite these strides, achieving cohesive multimod…
DiPO: Disentangled Perplexity Policy Optimization for Fine-grained Exploration-Exploitation Trade-Off
Xiaofan Li, Ming Yang, Zhiyuan Ma +9
Reinforcement Learning with Verifiable Rewards (RLVR) has catalyzed significant advances in the reasoning capabilities of Large Language Models (LLMs). However, effectively managin…
Evolution of Video Generative Foundations
Teng Hu, Jiangning Zhang, Hongrui Huang +7
The rapid advancement of Artificial Intelligence Generated Content (AIGC) has revolutionized video generation, enabling systems ranging from proprietary pioneers like OpenAI's Sora…
EgoSim: Egocentric World Simulator for Embodied Interaction Generation
Jinkun Hao, Mingda Jia, Ruiyan Wang +7
We introduce EgoSim, a closed-loop egocentric world simulator that generates spatially consistent interaction videos and persistently updates the underlying 3D scene state for cont…
S2GS: Streaming Semantic Gaussian Splatting for Online Scene Understanding and Reconstruction
Renhe Zhang, Yuyang Tan, Jingyu Gong +4
Existing offline feed-forward methods for joint scene understanding and reconstruction on long image streams often repeatedly perform global computation over an ever-growing set of…
S2D: Sparse to Dense Lifting for 3D Reconstruction with Minimal Inputs
Yuzhou Ji, Qijian Tian, He Zhu +5
Explicit 3D representations have already become an essential medium for 3D simulation and understanding. However, the most commonly used point cloud and 3D Gaussian Splatting (3DGS…
CLIP-Map: Structured Matrix Mapping for Parameter-Efficient CLIP Compression
Kangjie Zhang, Wenxuan Huang, Xin Zhou +9
Contrastive Language-Image Pre-training (CLIP) has achieved widely applications in various computer vision tasks, e.g., text-to-image generation, Image-Text retrieval and Image cap…