Computer Vision

Large-scale Codec Avatars: The Unreasonable Effectiveness of Large-scale Avatar Pretraining CVPR 2026 LaRP: Efficient Multi-View Inpainting with Latent Reprojection Priors CVPR 2026 LaS-Comp: Zero-shot 3D Completion with Latent-Spatial Consistency CVPR 2026 LASER: Layer-wise Scale Alignment for Training-Free Streaming 4D Reconstruction CVPR 2026 LASER: Lip Landmark Assisted Speaker Detection for Robustness WACV 2026 LASOR: Towards Clinically Transparent and Explainable Ophthalmic Report Generation via Lesion-Aware Segmentation WACV 2026 Latent Knowledge-Guided Video Diffusion for Scientific Phenomena Generation from a Single Initial Frame AAAI 2026 Latent Uncertainty-Aware Multi-View SDF Scan Completion WACV 2026 LATTICE: Democratize High-Fidelity 3D Generation at Scale CVPR 2026 LaVR: Scene Latent Conditioned Generative Video Trajectory Re-Rendering using Large 4D Reconstruction Models CVPR 2026 Layer Consistency Matters: Elegant Latent Transition Discrepancy for Generalizable Synthetic Image Detection CVPR 2026 Layered 4D-Rotor Gaussian Splatting: A Compressed Representation for Long Dynamic Scenes CVPR 2026 LayerEdit: Disentangled Multi-Object Editing via Conflict-Aware Multi-Layer Learning AAAI 2026 Layer-wise Instance Binding for Regional and Occlusion Control in Text-to-Image Diffusion Transformers CVPR 2026 LayoutAD: Exploring Semantic-Geometric Misalignment Reasoning for Scene Layout Anomaly Detection CVPR 2026 Layout Anything: One Transformer for Universal Room Layout Estimation WACV 2026 Laytrol: Preserving Pretrained Knowledge in Layout Control for Multimodal Diffusion Transformers AAAI 2026 LazyVAR: Accelerating Visual Autoregressive Models via Scale-wise Token Pruning and Parallel Group Decoding CVPR 2026 LDP-Slicing: Local Differential Privacy for Images via Randomized Bit-Plane Slicing CVPR 2026 LEADER: Learning Reliable Local-to-Global Correspondences for LiDAR Relocalization CVPR 2026 LEAD: Minimizing Learner-Expert Asymmetry in End-to-End Driving CVPR 2026 Learnability-Driven Submodular Optimization for Active Roadside 3D Detection CVPR 2026 Learnable Motion-Focused Tokenization for Effective and Efficient Video Unsupervised Domain Adaptation CVPR 2026 Learned Image Compression via Sparse Attention and Adaptive Frequency CVPR 2026 Learning 3D Occupancy from Beam Overlap in 2D Rotating mmWave Radar AAAI 2026