No article text was recorded for this version.
cascaded error propagation (2D-to-3D error propagation)
Version 2 of 2800 papers945 conceptsfrozen 2026-10-04
Papers in this version
- Blog: HMP: Hand Motion Priors for Pose and Shape Estimation from Video
- Blog: Camera Distortion-aware 3D Human Pose Estimation in Video with Optimization-based Meta-Learning
- Blog: HQ-OV3D: A High Box Quality Open-World 3D Detection Framework based on Diffision Model
- Blog: Frustum ConvNet: Sliding Frustums to Aggregate Local Point-Wise Features for Amodal
- Blog: FusionFormer: A Concise Unified Feature Fusion Transformer for 3D Pose Estimation
- Blog: PHD: Personalized 3D Human Body Fitting with Point Diffusion
- Blog: Multiview Detection with Cardboard Human Modeling
- Blog: Towards Alleviating the Modeling Ambiguity of Unsupervised Monocular 3D Human Pose Estimation
- Blog: StarPose: 3D Human Pose Estimation via Spatial-Temporal Autoregressive Diffusion
- Blog: Learning Pose Grammar to Encode Human Body Configuration for 3D Pose Estimation
- Blog: VoxelPose: Towards Multi-Camera 3D Human Pose Estimation in Wild Environment
- Blog: IDDR-NGP: Incorporating Detectors for Distractor Removal with Instant Neural Radiance Field
- Blog: Monocular 3D Object Detection Leveraging Accurate Proposals and Shape Reconstruction
- Blog: BOP Challenge 2024 on Model-Based and Model-Free 6D Object Pose Estimation
- Blog: View-Invariant Probabilistic Embedding for Human Pose
- Blog: Neural Descent for Visual 3D Human Pose and Shape
- Blog: Motion Guided 3D Pose Estimation from Videos
- Blog: HandGCAT: Occlusion-Robust 3D Hand Mesh Reconstruction from Monocular Images
- Blog: Hourglass Tokenizer for Efficient Transformer-Based 3D Human Pose Estimation
- Blog: High-Fidelity Neural Human Motion Transfer From Monocular Video
- Blog: Self-supervised Learning of Motion Capture
- Blog: H2OT: Hierarchical Hourglass Tokenizer for Efficient Video Pose Transformers
- Blog: Matching and Recovering 3D People from Multiple Views
- Blog: 3D Human Pose Regression using Graph Convolutional Network
- Blog: MAS: Multi-view Ancestral Sampling for 3D Motion Generation Using 2D Diffusion
- Blog: MonoGRNet: A Geometric Reasoning Network for Monocular 3D Object Localization
- Blog: Weakly-supervised Cross-view 3D Human Pose Estimation
- Blog: A Spatiotemporal Bidirectional Mamba Network with Global–Local Skeletal Enhancement for 3D Human Pose Estimation
- Blog: ImVoteNet: Boosting 3D Object Detection in Point Clouds with Image Votes
- Blog: RfD-Net: Point Scene Understanding by Semantic Instance Reconstruction
- Blog: 3D Bird Reconstruction: A Dataset, Model, and Shape Recovery from a Single View
- Blog: Fast and Robust Multi-Person 3D Pose Estimation From Multiple Views
- Blog: A Unified Deep Framework for Joint 3D Pose Estimation and Action Recognition from a Single RGB Camera
- Blog: Lifting 2d Human Pose to 3d : A Weakly Supervised Approach
- Blog: Evopose: A Recursive Transformer for 3D Human Pose Estimation with Kinematic Structure Priors
- Blog: Computer Vision to the Rescue: Infant Postural Symmetry Estimation from Incongruent Annotations
- Blog: Unsupervised Learning of 3D Scene Flow from Monocular Camera
- Blog: Rethinking Pseudo-LiDAR Representation
- Blog: 3D human pose estimation in video with temporal convolutions and semi-supervised training
- Blog: ProPLIKS: Probablistic 3D human body pose estimation
- Blog: Mitigating Trade-off: Stream and Query-guided Aggregation for Efficient and Effective 3D Occupancy Prediction
- Blog: Lifting by Image – Leveraging Image Cues for Accurate 3D Human Pose Estimation
- Blog: IPOD: Intensive Point-based Object Detector for Point Cloud
- Blog: 3D Object Detection Using Scale Invariant and Feature Reweighting Networks
- Blog: DID-M3D: Decoupling Instance Depth for Monocular 3D Object Detection
- Blog: NEAT: Distilling 3D Wireframes from Neural Attraction Fields
- Blog: MoCaNet: Motion Retargeting in-the-wild via Canonicalization Networks
- Blog: Instance-aware Multi-Camera 3D Object Detection with Structural Priors Mining and Self-Boosting Learning
- Blog: MixSTE: Seq2seq Mixed Spatio-Temporal Encoder for 3D Human Pose Estimation in Video
- Blog: FrustumFormer: Adaptive Instance-aware Resampling for Multi-view 3D Detection
- Blog: Online Test-time Adaptation for 3D Human Pose Estimation: A Practical Perspective with Estimated 2D Poses
- Blog: Transcribe3D: Grounding LLMs Using Transcribed Information for 3D Referential Reasoning with Self-Corrected Finetuning
- Blog: AbsPoseLifter: Absolute 3D Human Pose Lifting Network from a Single Noisy 2D Human Pose
- Blog: CameraPose: Weakly-Supervised Monocular 3D Human Pose Estimation by Leveraging In-the-wild 2D Annotations
- Blog: Dense Variational Reconstruction of Non-rigid Surfaces from Monocular Video
- Blog: 2D-Driven 3D Object Detection in RGB-D Images
- Blog: PointSee: Image Enhances Point Cloud
- Blog: 4D Association Graph for Realtime Multi-person Motion Capture Using Multiple Video Cameras
- Blog: Posegraphnet++: Enriching 3d Human Pose with Orientation Estimation
- Blog: RePOSE: 3D Human Pose Estimation via Spatio-Temporal Depth Relational Consistency
Showing 60 of 800 papers.
History & citation
Current · Permanent link
- The Recall Bottleneck in 2D-Driven 3D Detection merged into this direction (95% overlap)
Cite this direction
Latest version (a living page):
@misc{lacuna_cascaded_error_propagation_2d_to_3d_erro_befd8249,
title = {cascaded error propagation (2D-to-3D error propagation)},
author = {{Lacuna}},
howpublished = {Lacuna research direction},
year = {2026},
url = {https://lacuna.tiptreesystems.com/direction/cascaded-error-propagation-2d-to-3d-error-propagation/rdr_befd8249e51442a1bb479cc2a4ca4a6f},
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_cascaded_error_propagation_2d_to_3d_erro_befd8249_v2,
title = {cascaded error propagation (2D-to-3D error propagation)},
author = {{Lacuna}},
howpublished = {Lacuna research direction},
year = {2026},
url = {https://lacuna.tiptreesystems.com/direction/cascaded-error-propagation-2d-to-3d-error-propagation/rdr_befd8249e51442a1bb479cc2a4ca4a6f/v/2},
note = {Version 2, frozen 2026-10-04. Accessed 2026-11-19},
}