No article text was recorded for this version.
geometric task decoupling
Version 2 of 299 papers100 conceptsfrozen 2026-10-04
Papers in this version
- Blog: SemStereo: Semantic-Constrained Stereo Matching Network for Remote Sensing
- Blog: Flow2Stereo: Effective Self-Supervised Learning of Optical Flow and Stereo Matching
- Blog: PanopticDepth: A Unified Framework for Depth-aware Panoptic Segmentation
- Blog: Mutual Adaptive Reasoning for Monocular 3D Multi-Person Pose Estimation
- Blog: Learning Effective Geometry Representation from Videos for Self-Supervised Monocular Depth Estimation
- Blog: 3D Scene Understanding by Voxel-CRF
- Blog: See Yourself in Others: Attending Multiple Tasks for Own Failure Detection
- Blog: UnOS: Unified Unsupervised Optical-Flow and Stereo-Depth Estimation by Watching Videos
- Blog: Joint Stereo Video Deblurring, Scene Flow Estimation and Moving Object Segmentation
- Blog: Geometric Constrained Joint Lane Segmentation and Lane Boundary Detection
- Blog: GeoNet: Unsupervised Learning of Dense Depth, Optical Flow and Camera Pose
- Blog: Height and Uprightness Invariance for 3D Prediction From a Single View
- Blog: DF-Net: Unsupervised Joint Learning of Depth and Flow Using Cross-Task Consistency
- Blog: PVO: Panoptic Visual Odometry
- Blog: DEHRFormer: Real-time Transformer for Depth Estimation and Haze Removal from Varicolored Haze Scenes
- Blog: Decomposing a scene into geometric and semantically consistent regions
- Blog: Joint 3D Layout and Depth Prediction from a Single Indoor Panorama Image
- Blog: GasMono: Geometry-Aided Self-Supervised Monocular Depth Estimation for Indoor Scenes
- Blog: Towards Deeply Unified Depth-aware Panoptic Segmentation with Bi-directional Guidance Learning
- Blog: Mono-SF: Multi-View Geometry Meets Single-View Depth for Monocular Scene Flow Estimation of Dynamic Traffic Scenes
- Blog: ViPOcc: Leveraging Visual Priors from Vision Foundation Models for Single-View 3D Occupancy Prediction
- Blog: Seeing 3D objects in a single 2D image
- Blog: SA-BEV: Generating Semantic-Aware Bird's-Eye-View Feature for Multi-view 3D Object Detection
- Blog: Revealing the Reciprocal Relations between Self-Supervised Stereo and Monocular Depth Estimation
- Blog: StereoFlowGAN: Co-training for Stereo and Flow with Unsupervised Domain Adaptation
- Blog: Occlusion relationship reasoning with a feature separation and interaction network
- Blog: SfMLearner++: Learning Monocular Depth & Ego-Motion using Meaningful Geometric Constraints
- Blog: Joint Semantic Segmentation and Boundary Detection Using Iterative Pyramid Contexts
- Blog: SIU3R: Simultaneous Scene Understanding and 3D Reconstruction Beyond Feature Alignment
- Blog: Mono3DVLT: Monocular-Video-Based 3D Visual Language Tracking
- Blog: TiCoSS: Tightening the Coupling between Semantic Segmentation and Stereo Matching within A Joint Learning Framework
- Blog: Multi-task learning and joint refinement between camera localization and object detection
- Blog: Joint Learning of Semantic Alignment and Object Landmark Detection
- Blog: A coarse-to-fine model for 3D pose estimation and sub-category recognition
- Blog: Oriented Light-Field Windows for Scene Flow
- Blog: CoL3D: Collaborative Learning of Single-view Depth and Camera Intrinsics for Metric 3D Shape Recovery
- Blog: Seg4Reg+: Consistency Learning between Spine Segmentation and Cobb Angle Regression
- Blog: Towards Deeply Unified Depth-aware Panoptic Segmentation with Bi-directional Guidance Learning
- Blog: FLODCAST: Flow and Depth Forecasting via Multimodal Recurrent Architectures
- Blog: Self-supervised Monocular Depth and Pose Estimation for Endoscopy with Latent Priors
- Blog: The Edge of Depth: Explicit Constraints Between Segmentation and Depth
- Blog: Competitive Collaboration: Joint Unsupervised Learning of Depth, Camera Motion, Optical Flow and Motion Segmentation
- Blog: Learning Independent Object Motion From Unlabelled Stereoscopic Videos.
- Blog: Joint Face Detection and Alignment Using Multitask Cascaded Convolutional Networks
- Blog: Improving Online Lane Graph Extraction by Object-Lane Clustering
- Blog: Veritatem Dies Aperit - Temporally Consistent Depth Prediction Enabled by a Multi-Task Geometric and Semantic Scene Understanding Approach
- Blog: CasFusionNet: A Cascaded Network for Point Cloud Semantic Scene Completion by Dense Feature Fusion
- Blog: Estimating the 3D Layout of Indoor Scenes and Its Clutter from Depth Sensors
- Blog: Real-Time Semantic Stereo Matching
- Blog: CliffPhys: Camera-Based Respiratory Measurement Using Clifford Neural Networks
- Blog: Learning End-To-End Scene Flow by Distilling Single Tasks Knowledge
- Blog: Image Masking for Robust Self-Supervised Monocular Depth Estimation
- Blog: UFD-PRiME: Unsupervised Joint Learning of Optical Flow and Stereo Depth through Pixel-Level Rigid Motion Estimation
- Blog: DualRefine: Self-Supervised Depth and Pose Estimation Through Iterative Epipolar Sampling and Refinement Toward Equilibrium
- Blog: Joint Face Alignment and 3D Face Reconstruction with Application to Face Recognition
- Blog: Semantics-Depth-Symbiosis: Deeply Coupled Semi-Supervised Learning of Semantics and Depth
- Blog: Learning To Relate Depth and Semantics for Unsupervised Domain Adaptation
- Blog: Layered Interpretation of Street View Images
- Blog: Joint 3D Scene Reconstruction and Class Segmentation
- Blog: Semantics-Depth-Symbiosis: Deeply Coupled Semi-Supervised Learning of Semantics and Depth
Showing 60 of 99 papers.
History & citation
Current · Permanent link
Cite this direction
Latest version (a living page):
@misc{lacuna_geometric_task_decoupling_79e6d57c,
title = {geometric task decoupling},
author = {{Lacuna}},
howpublished = {Lacuna research direction},
year = {2026},
url = {https://lacuna.tiptreesystems.com/direction/geometric-task-decoupling/rdr_79e6d57c4ac84246b12c68a435152554},
note = {Latest version of a living research direction; cite a version for a fixed text. Accessed 2026-11-19},
}This exact version (version 2, frozen text):
@misc{lacuna_geometric_task_decoupling_79e6d57c_v2,
title = {geometric task decoupling},
author = {{Lacuna}},
howpublished = {Lacuna research direction},
year = {2026},
url = {https://lacuna.tiptreesystems.com/direction/geometric-task-decoupling/rdr_79e6d57c4ac84246b12c68a435152554/v/2},
note = {Version 2, frozen 2026-10-04. Accessed 2026-11-19},
}