arXiv:2609.24482v1 Announce Type: new Abstract: Monocular 3D human pose estimation (HPE) remains challenging due to depth ambiguity, occlu- sions, and the need for temporal consistency. While multi-v...
Human mesh recovery (HMR) aims to recover 3D human meshes from images. Most existing HMR benchmarks and methods focus on either multi-person reconstruction from a single view or single-person reconstruction from multiple views, where the number of subjects and the scene scale are relatively limited.
UT‑HMR is a one‑stage monocular 3D human mesh recovery framework that introduces uncertainty‑guided temporal modeling to address ambiguities caused by weak observations such as distance, occlusion, and motion blur. It predicts a Gaussian distribution over SMPL pose with a low‑rank-plus‑diagonal covariance, converting this into joint‑wise precision weights for heteroscedastic supervision while keeping inference deterministic. Temporal early fusion incorporates neighboring‑frame evidence before pose decoding, enabling the model to resolve pose ambiguities and achieve state‑of‑the‑art results on VIP‑HockeyPose‑v2, WorldPose, and competitive performance on 3DPW using a lightweight ViT‑B backbone.
arXiv:2603.25175v2 Announce Type: replace Abstract: Monocular egocentric 3D pose estimation is difficult because severe foreshortening, self-occlusion, and a restricted field of view often remove the...
The paper introduces PICO, an end-to-end trainable model for 6DoF surgical tool pose estimation that uses multi-task learning to predict segmentation, depth, and pose parameters. It incorporates two geometry-aware proxy tasks—a projection loss and a point-to-point loss—to enforce consistency in 2D and 3D spaces, improving accuracy and robustness. Evaluated on the SurgRIPE dataset, PICO achieves strong performance, ranking second in rotation accuracy and maintaining competitive translation results, especially under occlusion.
TriSAR-3D is a new trimodal dataset combining high‑resolution LiDAR, RGB, and thermal imagery to capture people in varied indoor and outdoor poses, including lying and partially occluded positions. The authors propose PaintFusion, a lightweight trimodal 3D detection pipeline that fuses PointPainting evidence with an MLP, achieving 65.4 AP@50 and outperforming LiDAR‑only, RGB+LiDAR, and other trimodal baselines while running faster (51.6 ms per frame). Experiments show that removing lying instances from training drastically reduces detection performance, highlighting the importance of dataset diversity for robust 3D person detection in search and rescue scenarios.
XCalib is an unsupervised dense registration framework that aligns thermal and visible video streams by optimizing virtual pinhole camera parameters and predicted monocular depth, thereby restricting spatial displacements to physically valid projection geometries. It introduces a novel registration paradigm using camera parameterization as an implicit regularizer, a robust Normalized Edges Correlation (NEC) metric for cross‑spectral alignment, and demonstrates superior temporal stability and alignment accuracy on public ADAS datasets compared to unconstrained dense flow baselines.
SituHOI is a large‑scale RGB‑D dataset that captures full‑body human‑object interactions in 16 indoor rooms, comprising 18,429 annotated clips and about 86 hours of activity. The dataset pairs moving‑camera recordings with static scene scans, object geometry, language descriptions, and estimated human and object trajectories, all registered in a shared floor‑aligned frame via a pipeline that integrates camera localization, depth‑based alignment, human mesh recovery, and object tracking. The data enable the FlexHOI‑Bench benchmark for goal‑conditioned joint motion prediction, and a reference predictor, SharedHOI, demonstrates strong performance on world‑space accuracy and human‑object coordination. whyItMatters":"The dataset provides scalable, scene‑aligned supervision for modeling human‑object interaction, addressing a key limitation of existing datasets and enabling more accurate motion prediction benchmarks."
TAPVid-MV is a new benchmark for tracking any point in 3D across multiple synchronized camera views. It comprises 284 sequences, 1,142 calibrated camera streams, and 109,769 point tracks, covering indoor and outdoor domains and derived from various modalities such as depth, LiDAR, SLAM, and simulation. The dataset is visually verified, and evaluation shows that current multi‑view trackers do not consistently outperform monocular trackers, highlighting geometry recovery as a key bottleneck.
PIVOT is a new multi‑trajectory dataset and evaluation framework that captures real‑world scenes with diverse camera paths, preserving both sensor‑derived measured poses and COLMAP‑optimized poses along with calibrated and optimized intrinsics. It defines three benchmark families—seen vs. unseen trajectory generalization, measured vs. optimized pose sensitivity, and calibrated vs. optimized intrinsics sensitivity—and introduces a directed pose‑space Chamfer distance to assess pose coverage. The first version of PIVOT includes five scenes recorded with a DJI Mini 4 Pro and offers an open processing and Nerfstudio‑based evaluation toolchain, revealing a consistent quality gap between held‑out and unseen trajectories and significant sensitivity to pose source and camera intrinsics.
arXiv:2504.15776v2 Announce Type: replace Abstract: Public autonomous driving datasets underpin the training and benchmarking of perception, mapping, and localization algorithms, yet residual inaccur...
arXiv:2606. 07053v1 Announce Type: cross Abstract: Pose-guided text-to-image generation often suffers from limb distortions and feature crosstalk in complex multi-person scenarios.