Imagen de Portada

MagicEraser: Erasing Any Objects via Semantics-Aware Control

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Li, Fan, Zhang, Zixiao, Huang, Yi, Liu, Jianzhuang, Pei, Renjing, Shao, Bin, Xu, Songcen
Formato:	Preprint
Publicado:	2024
Materias:	Computer Vision and Pattern Recognition
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

OutDreamer: Video Outpainting with a Diffusion Transformer
por: Zhong, Linhao, et al.
Publicado: (2025)

Receler: Reliable Concept Erasing of Text-to-Image Diffusion Models via Lightweight Erasers
por: Huang, Chi-Pin, et al.
Publicado: (2023)

AdaEraser: Training-Free Object Removal via Adaptive Attention Suppression
por: Liu, Dingming
Publicado: (2026)

MagicSeg: Open-World Segmentation Pretraining via Counterfactural Diffusion-Based Auto-Generation
por: Cai, Kaixin, et al.
Publicado: (2026)

LayerDiff: Exploring Text-guided Multi-layered Composable Image Synthesis via Layer-Collaborative Diffusion Model
por: Huang, Runhui, et al.
Publicado: (2024)

EraseDraw: Learning to Draw Step-by-Step via Erasing Objects from Images
por: Canberk, Alper, et al.
Publicado: (2024)

DeepEraser: Deep Iterative Context Mining for Generic Text Eraser
por: Feng, Hao, et al.
Publicado: (2024)

Federated Learning with Domain Shift Eraser
por: Wang, Zheng, et al.
Publicado: (2025)

AttriCLIP: A Non-Incremental Learner for Incremental Knowledge Learning
por: Wang, Runqi, et al.
Publicado: (2023)

GenEraser: Generalizable Video Object Removal via Balanced Text-Mask Guidance and Decoupled Locator-Preserver
por: Chen, Yuqing, et al.
Publicado: (2026)

Fuse Your Latents: Video Editing with Multi-source Latent Diffusion Models
por: Lu, Tianyi, et al.
Publicado: (2023)

AutoTVG: A New Vision-language Pre-training Paradigm for Temporal Video Grounding
por: Zhang, Xing, et al.
Publicado: (2024)

DSTSA-GCN: Advancing Skeleton-Based Gesture Recognition with Semantic-Aware Spatio-Temporal Topology Modeling
por: Cui, Hu, et al.
Publicado: (2025)

EffectErase: Joint Video Object Removal and Insertion for High-Quality Effect Erasing
por: Fu, Yang, et al.
Publicado: (2026)

OmniEraser: Remove Objects and Their Effects in Images with Paired Video-Frame Data
por: Wei, Runpu, et al.
Publicado: (2025)

Attentive Eraser: Unleashing Diffusion Model's Object Removal Potential via Self-Attention Redirection Guidance
por: Sun, Wenhao, et al.
Publicado: (2024)

Knowledge Transfer with Simulated Inter-Image Erasing for Weakly Supervised Semantic Segmentation
por: Chen, Tao, et al.
Publicado: (2024)

MirrorGaussian: Reflecting 3D Gaussians for Reconstructing Mirror Reflections
por: Liu, Jiayue, et al.
Publicado: (2024)

Decoupled Distillation to Erase: A General Unlearning Method for Any Class-centric Tasks
por: Zhou, Yu, et al.
Publicado: (2025)

Erase Diffusion: Empowering Object Removal Through Calibrating Diffusion Pathways
por: Liu, Yi, et al.
Publicado: (2025)

Accelerating Rectified Flow Models via Trajectory-Aware Caching
por: Liu, Xiao, et al.
Publicado: (2026)

ID-Eraser: Proactive Defense Against Face Swapping via Identity Perturbation
por: Luo, Junyan, et al.
Publicado: (2026)

SafeEraser: Enhancing Safety in Multimodal Large Language Models through Multimodal Machine Unlearning
por: Chen, Junkai, et al.
Publicado: (2025)

From Understanding to Erasing: Towards Complete and Stable Video Object Removal
por: Liu, Dingming, et al.
Publicado: (2026)

EraserDiT: Fast Video Inpainting with Diffusion Transformer Model
por: Liu, Jie, et al.
Publicado: (2025)

SAMPart3D: Segment Any Part in 3D Objects
por: Yang, Yunhan, et al.
Publicado: (2024)

TARA: Token-Aware LoRA for Composable Personalization in Diffusion Models
por: Peng, Yuqi, et al.
Publicado: (2025)

MagicRoad: Semantic-Aware 3D Road Surface Reconstruction via Obstacle Inpainting
por: Peng, Xingyue, et al.
Publicado: (2025)

Direction-Aware Hybrid Representation Learning for 3D Hand Pose and Shape Estimation
por: Liu, Shiyong, et al.
Publicado: (2025)

ActErase: A Training-Free Paradigm for Precise Concept Erasure via Activation Redirection
por: Sun, Yi, et al.
Publicado: (2026)

You Only Erase Once: Erasing Anything without Bringing Unexpected Content
por: Zhu, Yixing, et al.
Publicado: (2026)

VastGaussian: Vast 3D Gaussians for Large Scene Reconstruction
por: Lin, Jiaqi, et al.
Publicado: (2024)

AnyControl: Create Your Artwork with Versatile Control on Text-to-Image Generation
por: Sun, Yanan, et al.
Publicado: (2024)

Material Anything: Generating Materials for Any 3D Object via Diffusion
por: Huang, Xin, et al.
Publicado: (2024)

MagicDrive3D: Controllable 3D Generation for Any-View Rendering in Street Scenes
por: Gao, Ruiyuan, et al.
Publicado: (2024)

FreeScale: Scaling 3D Scenes via Certainty-Aware Free-View Generation
por: Jiang, Chenhan, et al.
Publicado: (2026)

DiffuEraser: A Diffusion Model for Video Inpainting
por: Li, Xiaowen, et al.
Publicado: (2025)

FixingGS: Enhancing 3D Gaussian Splatting via Training-Free Score Distillation
por: Wang, Zhaorui, et al.
Publicado: (2025)

Erased, But Not Forgotten: Erased Rectified Flow Transformers Still Remain Unsafe Under Concept Attack
por: Jiang, Nanxiang, et al.
Publicado: (2025)

FlowErase-RL: Rethinking Concept Erasure as Reward Optimization in Flow Matching Models
por: Sun, Yi, et al.
Publicado: (2026)