activity
20182026
most citedAdR-Gaussian: Accelerating Gaussian Splatting with Adaptive Radius

35 citations · 275 across the 111 of their papers we have counts for

collaborators

112 papers

cs.CV2026

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…

cs.CV2026

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…

cs.CV2026

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…

cs.CV2026

VicEdit: Learning to Edit Videos from Visual In-Context Examples

Yuji Wang, Teng Hu, Yuheng Chen +6

Despite progress in instruction-based video editing, unimodal textual instructions inherently struggle to convey fine-grained textures and complex dynamics. To bridge this perceptu…

cs.CV2026

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…

cs.CV2026

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…