近期论文13
- MorphAny3D: Unleashing the Power of Structured Latent in 3D Morphing第 4 位,共 6 位作者CVPR 2026 · 5 次引用
- Adaptive Depth Lightweight RGB-T Tracking with Holistic Token Routing第 7 位,共 7 位作者CVPR 2026 · 3 次引用
- CoDi: Subject-Consistent and Pose-Diverse Text-to-Image Generation第 5 位,共 5 位作者ICLR 2026 · 1 次引用
- Muses: Designing, Composing, Generating Nonexistent Fantasy 3D Creatures without Training第 5 位,共 7 位作者CVPR 2026
- VINS-120K: Ultra High-Resolution Image Editing with A Large-Scale Dataset第 9 位,共 9 位作者CVPR 2026
- Exploiting Multimodal Spatial-temporal Patterns for Video Object Tracking第 2 位,共 8 位作者AAAI 2025 · 65 次引用
- Guided Real Image Dehazing Using YCbCr Color Space第 5 位,共 6 位作者AAAI 2025 · 46 次引用
- StrandHead: Text to Hair-Disentangled 3D Head Avatars Using Human-Centric Priors第 3 位,共 5 位作者ICCV 2025 · 3 次引用
- Category-Aware 3D Object Composition with Disentangled Texture and Shape Multi-view Diffusion第 5 位,共 7 位作者ACM MM 2025 · 2 次引用
- Learning Generalized Residual Exchange-Correlation-Uncertain Functional for Density Functional Theory第 4 位,共 5 位作者AAAI 2025 · 1 次引用
- Describe, Don't Dictate: Semantic Image Editing with Natural Language Intent第 8 位,共 8 位作者ICCV 2025
- OpenVid-1M: A Large-Scale High-Quality Dataset for Text-to-video Generation第 9 位,共 9 位作者ICLR 2025
- MambaLLIE: Implicit Retinex-Aware Low Light Enhancement with Global-then-Local State Space第 3 位,共 6 位作者NeurIPS 2024 · 118 次引用
