One Model for ALL: Low-Level Task Interaction Is a Key to Task-Agnostic Image Fusion
Comments Accepted by CVPR 2025 v2
期刊&会议
CVPR
Conference on Computer Vision and Pattern Recognition · 会议 · Computer Vision
Universal Actions for Enhanced Embodied Foundation Models
Comments CVPR 2025
Mask-Adapter: The Devil is in the Masks for Open-Vocabulary Segmentation
Comments Accepted by CVPR 2025; Code & models: https://github.com/hustvl/MaskAdapter
UniVAD: A Training-free Unified Model for Few-shot Visual Anomaly Detection
Comments Accepted by CVPR 2025; Project page: https://uni-vad.github.io/
Adversarial Diffusion Compression for Real-World Image Super-Resolution
Comments Accepted by CVPR 2025
QMambaBSR: Burst Image Super-Resolution with Query State Space Model
Comments Accepted by CVPR 2025
Mind the Time: Temporally-Controlled Multi-Event Video Generation
Comments CVPR 2025. Project Page: https://mint-video.github.io/
Driving-Video Dehazing with Non-Aligned Regularization for Safety Assistance
Comments Accepted by CVPR 2024
AIM-Fair: Advancing Algorithmic Fairness via Selectively Fine-Tuning Biased Models with Contextual Synthetic Data
Comments Accepted at CVPR 2025. Github: https://github.com/zengqunzhao/AIM-Fair. Project page: https://zengqunzhao.github.io/AIMFair
NoT: Federated Unlearning via Weight Negation
Comments The 42nd IEEE/CVF Conference on Computer Vision and Pattern Recognition, Nashville TN, US. 2025
Completion as Enhancement: A Degradation-Aware Selective Image Guided Network for Depth Completion
Comments CVPR 2025
CARTO: Category and Joint Agnostic Reconstruction of ARTiculated Objects
Comments 20 pages, 11 figures, accepted at CVPR 2023
Enhancing SAM with Efficient Prompting and Preference Optimization for Semi-supervised Medical Image Segmentation
Comments Accepted to CVPR 2025
IMFine: 3D Inpainting via Geometry-guided Multi-view Refinement
Comments Accepted at CVPR 2025, \href{https://xinxinzuo2353.github.io/imfine/}{Project Page}
SMTPD: A New Benchmark for Temporal Prediction of Social Media Popularity
Comments accept by CVPR 2025
S2Gaussian: Sparse-View Super-Resolution 3D Gaussian Splatting
Comments CVPR 2025
Synthetic Data is an Elegant GIFT for Continual Vision-Language Models
Comments This work is accepted by CVPR 2025. Modifications may be performed
Q-PART: Quasi-Periodic Adaptive Regression with Test-time Training for Pediatric Left Ventricular Ejection Fraction Regression
Comments Accepted to CVPR 2025
SCSA: A Plug-and-Play Semantic Continuous-Sparse Attention for Arbitrary Semantic Style Transfer
Comments Accepted by CVPR 2025
Self-Supervised Large Scale Point Cloud Completion for Archaeological Site Restoration
Comments Accepted at CVPR 2025
ReRAW: RGB-to-RAW Image Reconstruction via Stratified Sampling for Efficient Object Detection on the Edge
Comments Accepted at CVPR 2025
LION-FS: Fast & Slow Video-Language Thinker as Online Video Assistant
Comments Accept to CVPR 2025, Project page: https://github.com/JiuTian-VL/LION-FS
Towards Effective and Sparse Adversarial Attack on Spiking Neural Networks via Breaking Invisible Surrogate Gradients
Comments Accepted by CVPR 2025
DSPNet: Dual-vision Scene Perception for Robust 3D Question Answering
Comments Accepted by CVPR 2025
OmniGuard: Hybrid Manipulation Localization via Augmented Versatile Deep Image Watermarking
Comments Accepted by CVPR 2025
LaVin-DiT: Large Vision Diffusion Transformer
Comments 37 pages, 30 figures, 4 tables. Accepted by CVPR 2025
EgoExoLearn: A Dataset for Bridging Asynchronous Ego- and Exo-centric View of Procedural Activities in Real World
Comments CVPR 2024
GEN3C: 3D-Informed World-Consistent Video Generation with Precise Camera Control
Comments To appear in CVPR 2025. Website: https://research.nvidia.com/labs/toronto-ai/GEN3C/
DoraCycle: Domain-Oriented Adaptation of Unified Generative Model in Multimodal Cycles
Comments CVPR 2025
CLIP is Strong Enough to Fight Back: Test-time Counterattacks towards Zero-shot Adversarial Robustness of CLIP
Comments Accepted to CVPR 2025
