LoRA Subtraction for Drift-Resistant Space in Exemplar-Free Continual Learning
Comments Accepted to CVPR 2025
期刊&会议
CVPR
Conference on Computer Vision and Pattern Recognition · 会议 · Computer Vision
Data-free Universal Adversarial Perturbation with Pseudo-semantic Prior
Comments CVPR 2025
Finer-CAM: Spotting the Difference Reveals Finer Details for Visual Explanation
Comments Accepted by CVPR 2025
Reversible Decoupling Network for Single Image Reflection Removal
Comments To appear at CVPR 2025
Consistency-aware Self-Training for Iterative-based Stereo Matching
Comments Accepted by CVPR 2025
Exploring Temporal Dynamics in Event-based Eye Tracker
Comments Accepted by CVPR 2025 Event-based Vision Workshop
HOIGen-1M: A Large-scale Dataset for Human-Object Interaction Video Generation
Comments CVPR 2025
3D Dental Model Segmentation with Geometrical Boundary Preserving
Comments The IEEE/CVF Conference on Computer Vision and Pattern Recognition 2025
Enhancing Creative Generation on Stable Diffusion-based Models
Comments CVPR 2025 accepted paper
COSMIC: Clique-Oriented Semantic Multi-space Integration for Robust CLIP Test-Time Adaptation
Comments Accepted to CVPR 2025
SketchVideo: Sketch-based Video Generation and Editing
Comments CVPR 2025
Language Guided Concept Bottleneck Models for Interpretable Continual Learning
Comments CVPR 2025; Project Page: https://github.com/FisherCats/CLG-CBM
AnyCam: Learning to Recover Camera Poses and Intrinsics from Casual Videos
Comments CVPR 2025 - For more details and code, please check out our project page under https://fwmb.github.io/anycam
Z-SASLM: Zero-Shot Style-Aligned SLI Blending Latent Manipulation
Comments Accepted to the CVPR 2025 Workshop AI for Creative Visual Content Generation Editing and Understanding
Large Self-Supervised Models Bridge the Gap in Domain Adaptive Object Detection
Comments 16 pages (8 main), 5 figures, accepted at CVPR 2025
LSNet: See Large, Focus Small
Comments CVPR 2025 Camera-ready Version
FRAME: Floor-aligned Representation for Avatar Motion from Egocentric Video
Comments Accepted at CVPR 2025
Empowering Large Language Models with 3D Situation Awareness
Comments Accepted by CVPR 2025
OmniMMI: A Comprehensive Multi-modal Interaction Benchmark in Streaming Video Contexts
Comments To appear at CVPR 2025
DIFFER: Disentangling Identity Features via Semantic Cues for Clothes-Changing Person Re-ID
Comments Accepted in CVPR 2025
GenFusion: Closing the Loop between Reconstruction and Generation via Videos
Comments CVPR 2025, project page: https://genfusion.sibowu.com
FireEdit: Fine-grained Instruction-based Image Editing via Region-aware Vision Language Model
Comments Accepted to CVPR 2025
Resilient Sensor Fusion under Adverse Sensor Failures via Multi-Modal Expert Fusion
Comments Accepted to CVPR 2025
Bootstrap Your Own Views: Masked Ego-Exo Modeling for Fine-grained View-invariant Video Representations
Comments CVPR 2025 Camera-ready, 18 pages, 7 figures, 9 tables
Unified Uncertainty-Aware Diffusion for Multi-Agent Trajectory Modeling
Comments Accepted to CVPR 2025 conference
MonoInstance: Enhancing Monocular Priors via Multi-view Instance Alignment for Neural Rendering and Reconstruction
Comments Accepted by CVPR 2025. Project page: https://wen-yuan-zhang.github.io/MonoInstance/
NeRFPrior: Learning Neural Radiance Field as a Prior for Indoor Scene Reconstruction
Comments Accepted by CVPR 2025. Project page: https://wen-yuan-zhang.github.io/NeRFPrior/
TopV: Compatible Token Pruning with Inference Time Optimization for Fast and Low-Memory Multimodal Vision Language Model
Comments Accepted by CVPR 2025
Finsler Multi-Dimensional Scaling: Manifold Learning for Asymmetric Dimensionality Reduction and Embedding
Comments Accepted for publication at the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) 2025
Missing Target-Relevant Information Prediction with World Model for Accurate Zero-Shot Composed Image Retrieval
Comments This work has been accepted to CVPR 2025
