Computer Vision

RetouchIQ: MLLM Agents for Instruction-Based Image Retouching with Generalist Reward CVPR 2026 ReTrack: Evidence-Driven Dual-Stream Directional Anchor Calibration Network for Composed Video Retrieval AAAI 2026 Retrieve and Segment: Are a Few Examples Enough to Bridge the Supervision Gap in Open-Vocabulary Segmentation? CVPR 2026 Retrieve-to-Restore: Efficient All-in-One Image Restoration with a Retrieval-Based Degradation Bank CVPR 2026 ReVAD: From Imitation to Reasoning in Vectorized Autonomous Driving via Latent Space Search UAI 2026 Revealing and Reducing Morphological Biases Using Implicit Neural Representations for Medical Image Registration MIDL 2026 Revealing the Invisible: Latent Structure Modeling for Semantically Consistent Cloud Removal AAAI 2026 Reverse Personalization WACV 2026 RevINN: An End-to-End Invertible Neural Network for Reversible Adversarial Examples Generation CVPR 2026 Revisiting 3D Reconstruction Kernels as Low-Pass Filters CVPR 2026 Revisiting an Old Perspective Projection for Monocular 3D Morphable Models Regression WACV 2026 Revisiting Attention in the Dark for Low-Light Person Re-Identiffcation AAAI 2026 Revisiting Cross-Architecture Distillation: Adaptive Dual-Teacher Transfer for Lightweight Video Models AAAI 2026 Revisiting Downsampling in Semantic Segmentation: Fighting Aliasing with Dynamic Gaussian and Gabor Frequency Filters AAAI 2026 Revisiting foundation models for cell instance segmentation MIDL 2026 Revisiting Layer Normalization for Point Cloud Test Time Adaptation WACV 2026 Revisiting Monocular SLAM with Spatio-Temporal Scene Modeling CVPR 2026 Revisiting Network Inertia: Dynamic Inertia Inhibition Coupled Multidimensional Periodicity for Infrared and Visible Image Fusion AAAI 2026 Revisiting Optimal Coding for I-ToF under Practical Sensor Constraints CVPR 2026 Revisiting Pose Sensitivity in Splat-based Computed Tomography under Sparse-view Reconstruction CVPR 2026 Revisiting Retentive Networks for Fast Range-View 3D LiDAR Semantic Segmentation WACV 2026 Revisiting the Necessity of Full Accuracy: Weakly Supervised Object-Level Offset Correction for Misaligned Building Labels CVPR 2026 Revisiting Token Compression for Accelerating ViT-based Sparse Multi-View 3D Object Detectors CVPR 2026 Revisiting Vision-Language Foundations for No-Reference Image Quality Assessment WACV 2026 REVISOR: Beyond Textual Reflection, Towards Multimodal Introspective Reasoning in Long-Form Video Understanding CVPR 2026