dense prediction

3D-Aware Multi-Task Learning with Cross-View Correlations for Dense Scene Understanding CVPR 2026 ALLNet: Multi-task Dense Prediction for Degraded Images CVPR 2026 Beyond the Encoder: Joint Encoder-Decoder Contrastive Pre-Training Improves Dense Prediction WACV 2026 DAPE: Harmonizing Content-Position Encoding for Versatile Dense Visual Prediction AAAI 2026 Decomposition Sampling for Efficient Region Annotations in Active Learning WACV 2026 DPBridge: Latent Diffusion Bridge for Dense Prediction WACV 2026 FE2E: From Editor to Dense Geometry Estimator CVPR 2026 HAD: Heterogeneity-Aware Distillation for Lifelong Heterogeneous Learning CVPR 2026 In Pursuit of Pixel Supervision for Visual Pre-training CVPR 2026 LiDeRe: A Lightweight Readout for Fast and Data-Efficient Dense Prediction CVPR 2026 NexusFlow: Unifying Disparate Tasks under Partial Supervision via Invertible Flow Networks CVPR 2026 Parameter-, Memory-, Time-Efficient Multi-Task Dense Vision Adaptation AAAI 2026 S2C2Seg: Semantic-Spatial Consistency and Category Optimization for Open-Vocabulary Segmentation CVPR 2026 Shoe Style-Invariant and Ground-Aware Learning for Dense Foot Contact Estimation CVPR 2026 StableMTL: Repurposing Latent Diffusion Models for Multi-Task Learning from Partially Annotated Synthetic Datasets CVPR 2026 Target Refocusing via Attention Redistribution for Open-Vocabulary Semantic Segmentation: An Explainability Perspective AAAI 2026 The Missing Point in Vision Transformers for Universal Image Segmentation CVPR 2026 The Power of Prior: Training-Free Open-Vocabulary Semantic Segmentation with LLaVA CVPR 2026 UniRefiner: Teaching Pre-trained ViTs to Self-Dispose Dross via Contrastive Register CVPR 2026 X-band Radar Non-Line-of-Sight Imaging CVPR 2026 Articulate3D: Holistic Understanding of 3D Scenes as Universal Scene Description ICCV 2025 A Simple yet Mighty Hartley Diffusion Versatilist for Generalizable Dense Vision Tasks ICCV 2025 CR2PQ: Continuous Relative Rotary Positional Query for Dense Visual Representation Learning ICLR 2025 DeCLIP: Decoupled Learning for Open-Vocabulary Dense Perception CVPR 2025 FreeDNA: Endowing Domain Adaptation of Diffusion-Based Dense Prediction with Training-Free Domain Noise Alignment ICCV 2025