No article text was recorded for this version.
physically inconsistent data augmentation
Version 1 of 1162 papers215 conceptsfrozen 2026-10-04
Papers in this version
- Blog: Camera Pose Matters: Improving Depth Prediction by Mitigating Pose Distribution Bias
- Blog: 3D Copy-Paste: Physically Plausible Object Insertion for Monocular 3D Detection
- Blog: Plugging Self-Supervised Monocular Depth into Unsupervised Domain Adaptation for Semantic Segmentation
- Blog: IncreACO: Incrementally Learned Automatic Check-out with Photorealistic Exemplar Augmentation
- Blog: Context-Aware Data Augmentation for LIDAR 3d Object Detection
- Blog: What You See is What You Get: Exploiting Visibility for 3D Object Detection
- Blog: Three Ways to Improve Semantic Segmentation with Self-Supervised Depth Estimation
- Blog: Three Ways to Improve Semantic Segmentation with Self-Supervised Depth Estimation
- Blog: MonoLSS: Learnable Sample Selection For Monocular 3D Detection
- Blog: Three Ways To Improve Semantic Segmentation With Self-Supervised Depth Estimation
- Blog: WALT3D: Generating Realistic Training Data from Time-Lapse Imagery for Reconstructing Dynamic Objects Under Occlusion
- Blog: Semi-Supervised Semantic Depth Estimation using Symbiotic Transformer and NearFarMix Augmentation
- Blog: Transferring to Real-World Layouts: A Depth-aware Framework for Scene Adaptation
- Blog: Improving Semi-Supervised and Domain-Adaptive Semantic Segmentation with Self-Supervised Depth Estimation
- Blog: Perspective Aware Road Obstacle Detection
- Blog: Amodal Cityscapes: A New Dataset, its Generation, and an Amodal Semantic Segmentation Challenge Baseline
- Blog: Semantically Controllable Augmentations for Generalizable Robot Learning
- Blog: Diversified and Realistic 3D Augmentation via Iterative Construction, Random Placement, and HPR Occlusion
- Blog: LiDAR-Aug: A General Rendering-Based Augmentation Framework for 3D Object Detection
- Blog: 3D Random Occlusion and Multi-layer Projection for Deep Multi-camera Pedestrian Localization
- Blog: GRAMO: geometric resampling augmentation for monocular 3D object detection
- Blog: Perspective Aware Road Obstacle Detection
- Blog: Mitigating Object Dependencies: Improving Point Cloud Self-Supervised Learning Through Object Exchange
- Blog: DSGN++: Exploiting Visual-Spatial Relation for Stereo-based 3D Detectors
- Blog: Beyond Background Shift: Rethinking Instance Replay in Continual Semantic Segmentation
- Blog: What You See is What You Get: Exploiting Visibility for 3D Object Detection
- Blog: FairScene: Learning Class-Disentangled 2D/3D Representations for Semantic Scene Completion
- Blog: Semantics-Depth-Symbiosis: Deeply Coupled Semi-Supervised Learning of Semantics and Depth
- Blog: Semi-supervised Object Detection with Adaptive Class-Rebalancing Self-Training
- Blog: MonoPlace3D: Learning 3D-Aware Object Placement for 3D Monocular Detection
- Blog: Exploring Geometric Consistency for Monocular 3D Object Detection
- Blog: A High-Resolution Dataset for Instance Detection with Multi-View Object Capture
- Blog: ONCE-3DLanes: Building Monocular 3D Lane Detection
- Blog: 3D Copy-Paste: Physically Plausible Object Insertion for Monocular 3D Detection
- Blog: PhysAug: A Physical-guided and Frequency-based Data Augmentation for Single-Domain Generalized Object Detection
- Blog: Data Priming Network for Automatic Check-Out
- Blog: Few-Shot Learning via Saliency-Guided Hallucination of Samples
- Blog: Auto Cherry-Picker: Learning from High-quality Generative Data Driven by Language
- Blog: Appearance Fault Diagnosis of a Transformer Based on Data Set Optimization and Heterogeneous Model Ensemble
- Blog: StuffNet: Using 'Stuff' to Improve Object Detection
- Blog: Trainable Pointwise Decoder Module for Point Cloud Segmentation
- Blog: A Fast Data Collection and Augmentation Procedure for Object Recognition
- Blog: Training a Computer Vision Model for Commercial Bakeries with Primarily Synthetic Images
- Blog: Alleviating Foreground Sparsity for Semi-Supervised Monocular 3D Object Detection
- Blog: Exploring Scene Coherence for Semi-Supervised 3D Semantic Segmentation
- Blog: Context-Aware Mixup for Domain Adaptive Semantic Segmentation
- Blog: Automatic Drywall Analysis for Progress Tracking and Quality Control in Construction
- Blog: Lightweight Spatial Embedding for Vision-based 3D Occupancy Prediction
- Blog: Making Invisible Visible: Data-Driven Seismic Inversion With Spatio-Temporally Constrained Data Augmentation
- Blog: STD-PD: Generating Synthetic Training Data for Pedestrian Detection in Unannotated Videos
- Blog: SAM-guided Unsupervised Domain Adaptation for 3D Segmentation
- Blog: On the Importance of Visual Context for Data Augmentation in Scene Understanding
- Blog: Bidirectional Domain Mixup for Domain Adaptive Semantic Segmentation
- Blog: Generalizable Multi-Camera 3D Object Detection from a Single Source via Fourier Cross-View Learning
- Blog: CSOT: Cross-scan Object Transfer for Semi-Supervised LiDAR Object Detection
- Blog: Learning Class Prototypes for Unified Sparse-Supervised 3D Object Detection
- Blog: Bidirectional Domain Mixup for Domain Adaptive Semantic Segmentation
- Blog: 3D Data Augmentation for Driving Scenes on Camera
- Blog: SA-BEV: Generating Semantic-Aware Bird's-Eye-View Feature for Multi-view 3D Object Detection
- Blog: Monocular 3D Object Detection with Depth from Motion
Showing 60 of 162 papers.
History & citation
Current · Permanent link
- Contextual Object Placement for Robust Scene Understanding merged into this direction (50% overlap)
- Geometry Aware Data Augmentation for Scene Understanding merged into this direction (65% overlap)
- Geometry-Aware Data Augmentation for Scene Understanding merged into this direction (91% overlap)
Cite this direction
Latest version (a living page):
@misc{lacuna_physically_inconsistent_data_augmentatio_10d08f20,
title = {physically inconsistent data augmentation},
author = {{Lacuna}},
howpublished = {Lacuna research direction},
year = {2026},
url = {https://lacuna.tiptreesystems.com/direction/physically-inconsistent-data-augmentation/rdr_10d08f204fe24a839b017b6e074e7838},
note = {Latest version of a living research direction; cite a version for a fixed text. Accessed 2026-11-21},
}This exact version (version 1, frozen text):
@misc{lacuna_physically_inconsistent_data_augmentatio_10d08f20_v1,
title = {physically inconsistent data augmentation},
author = {{Lacuna}},
howpublished = {Lacuna research direction},
year = {2026},
url = {https://lacuna.tiptreesystems.com/direction/physically-inconsistent-data-augmentation/rdr_10d08f204fe24a839b017b6e074e7838/v/1},
note = {Version 1, frozen 2026-10-04. Accessed 2026-11-21},
}