Image de couverture de livre

TRACE: Your Diffusion Model is Secretly an Instance Edge Detector

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Jo, Sanghyun, Lee, Ziseok, Lee, Wooyeol, Choi, Jonghyun, Park, Jaesik, Kim, Kyungsu
Format:	Preprint
Publié:	2025
Sujets:	Computer Vision and Pattern Recognition
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

ISAC: Training-Free Instance-to-Semantic Attention Control for Improving Multi-Instance Generation
par: Jo, Sanghyun, et autres
Publié: (2025)

Early Timestep Zero-Shot Candidate Selection for Instruction-Guided Image Editing
par: Kim, Joowon, et autres
Publié: (2025)

One Click per Cell Type Suffices: Training-free Group Interaction for Cell Instance Segmentation
par: Jo, Sanghyun, et autres
Publié: (2026)

DHR: Dual Features-Driven Hierarchical Rebalancing in Inter- and Intra-Class Regions for Weakly-Supervised Semantic Segmentation
par: Jo, Sanghyun, et autres
Publié: (2024)

EraseLoRA: MLLM-Driven Foreground Exclusion and Background Subtype Aggregation for Dataset-Free Object Removal
par: Jo, Sanghyun, et autres
Publié: (2025)

COIN: Confidence Score-Guided Distillation for Annotation-Free Cell Segmentation
par: Jo, Sanghyun, et autres
Publié: (2025)

TTD: Text-Tag Self-Distillation Enhancing Image-Text Alignment in CLIP to Alleviate Single Tag Bias
par: Jo, Sanghyun, et autres
Publié: (2024)

FreeTimeGS++: Secrets of Dynamic Gaussian Splatting and Their Principles
par: Lee, Lucas Yunkyu, et autres
Publié: (2026)

Enhancing Creative Generation on Stable Diffusion-based Models
par: Han, Jiyeon, et autres
Publié: (2025)

Distribution Matching Distillation without Fake Score Network
par: Kim, Youngjoong, et autres
Publié: (2026)

Recovering Dynamic 3D Sketches from Videos
par: Lee, Jaeah, et autres
Publié: (2025)

3Doodle: Compact Abstraction of Objects with 3D Strokes
par: Choi, Changwoon, et autres
Publié: (2024)

PAC-FNO: Parallel-Structured All-Component Fourier Neural Operators for Recognizing Low-Quality Images
par: Jeon, Jinsung, et autres
Publié: (2024)

REVIVE 3D: Refinement via Encoded Voluminous Inflated prior for Volume Enhancement
par: Lee, Hankyeol, et autres
Publié: (2026)

Advanced Knowledge Transfer: Refined Feature Distillation for Zero-Shot Quantization in Edge Computing
par: Hong, Inpyo, et autres
Publié: (2024)

RoAD Benchmark: How LiDAR Models Fail under Coupled Domain Shifts and Label Evolution
par: Lee, Subeen, et autres
Publié: (2026)

VideoPatchCore: An Effective Method to Memorize Normality for Video Anomaly Detection
par: Ahn, Sunghyun, et autres
Publié: (2024)

Safety Alignment Backfires: Preventing the Re-emergence of Suppressed Concepts in Fine-tuned Text-to-Image Diffusion Models
par: Kim, Sanghyun, et autres
Publié: (2024)

Deep Cost Ray Fusion for Sparse Depth Video Completion
par: Kim, Jungeon, et autres
Publié: (2024)

Impact of Regularization on Calibration and Robustness: from the Representation Space Perspective
par: Park, Jonghyun, et autres
Publié: (2024)

See and Fix the Flaws: Enabling VLMs and Diffusion Models to Comprehend Visual Artifacts via Agentic Data Synthesis
par: Park, Jaehyun, et autres
Publié: (2026)

Diverse Rare Sample Generation with Pretrained GANs
par: Lee, Subeen, et autres
Publié: (2024)

OFF-CLIP: Improving Normal Detection Confidence in Radiology CLIP with Simple Off-Diagonal Term Auto-Adjustment
par: Park, Junhyun, et autres
Publié: (2025)

Attention Misses Visual Risk: Risk-Adaptive Steering for Multimodal Safety Alignment
par: Park, Jonghyun, et autres
Publié: (2025)

Safeguard Text-to-Image Diffusion Models with Human Feedback Inversion
par: Kim, Sanghyun, et autres
Publié: (2024)

HyGE-Occ: Hybrid View-Transformation with 3D Gaussian and Edge Priors for 3D Panoptic Occupancy Prediction
par: Kim, Jong Wook, et autres
Publié: (2025)

Improving Editability in Image Generation with Layer-wise Memory
par: Kim, Daneul, et autres
Publié: (2025)

GranQ: Efficient Channel-wise Quantization via Vectorized Pre-Scaling for Zero-Shot QAT
par: Hong, Inpyo, et autres
Publié: (2025)

InstantDrag: Improving Interactivity in Drag-based Image Editing
par: Shin, Joonghyuk, et autres
Publié: (2024)

Exploring Multimodal Diffusion Transformers for Enhanced Prompt-based Image Editing
par: Shin, Joonghyuk, et autres
Publié: (2025)

Granular Concept Circuits: Toward a Fine-Grained Circuit Discovery for Concept Representations
par: Kwon, Dahee, et autres
Publié: (2025)

OpenBox: Annotate Any Bounding Boxes in 3D
par: Lee, In-Jae, et autres
Publié: (2025)

Efficient Diffusion-Driven Corruption Editor for Test-Time Adaptation
par: Oh, Yeongtak, et autres
Publié: (2024)

CF3: Compact and Fast 3D Feature Fields
par: Lee, Hyunjoon, et autres
Publié: (2025)

TRACE: Trajectory-Constrained Concept Erasure in Diffusion Models
par: Carter, Finn
Publié: (2025)

Model Already Knows the Best Noise: Bayesian Active Noise Selection via Attention in Video Diffusion Model
par: Kim, Kwanyoung, et autres
Publié: (2025)

AnyAnomaly: Zero-Shot Customizable Video Anomaly Detection with LVLM
par: Ahn, Sunghyun, et autres
Publié: (2025)

Metropolis-Hastings Sampling for 3D Gaussian Reconstruction
par: Kim, Hyunjin, et autres
Publié: (2025)

Compose and Conquer: Diffusion-Based 3D Depth Aware Composable Image Synthesis
par: Lee, Jonghyun, et autres
Publié: (2024)

On the Collapse of Generative Paths: A Criterion and Correction for Diffusion Steering
par: Lee, Ziseok, et autres
Publié: (2025)