MetricTrail is a streaming system that accurately estimates camera motion and performs dense 3D reconstruction from long monocular videos. It leverages single‑image metric depth to improve trajectory accuracy without retraining the correspondence network or enlarging the optimization window, and uses learned adapters to enhance feature matching with frozen DINOv3 representations. The modular design allows independent upgrades of the depth provider, supports supplied camera intrinsics and calibrated stereo data, and achieves the lowest average trajectory error on KITTI, Oxford Spires, and VBR under RGB‑only protocols while delivering strong dense reconstructions on indoor, outdoor, and in‑the‑wild benchmarks.
arXiv:2608.27529v1 Announce Type: new Abstract: Streaming 3D reconstruction from extremely long videos requires estimating camera motion and scene geometry online under bounded memory and computation...
Kineo is a fully automatic, calibration‑free pipeline that performs markerless motion capture using unsynchronized, uncalibrated consumer‑grade RGB cameras. It uses 2D keypoints from existing detectors to jointly calibrate cameras (including distortion), reconstruct 3D keypoints, and generate dense scene pointmaps at metric scale. The method introduces confidence‑aware subsampling, graph‑based optimization, and a pairwise reprojection consistency score to achieve robust calibration and accurate metric scale recovery, achieving significant error reductions on EgoHumans and Human3.6M datasets while remaining computationally efficient.
arXiv:2601. 22054v2 Announce Type: replace-cross Abstract: Scaling has powered recent advances in vision foundation models, yet extending this paradigm to metric depth estimation remains challenging due to heterogeneous sensor noise, camera-dependent biases, and metric ambiguity in noisy cross-source 3D data.
Streaming 3D reconstruction relies on a compact recurrent scene state to process long image streams in linear time and bounded memory. However, repeated updates can gradually corrupt this state, causing reliable historical information to be overwritten by noisy or ambiguous observations.
arXiv:2501.12375v4 Announce Type: replace Abstract: Depth Anything has achieved remarkable success in monocular depth estimation with strong generalization ability. However, it suffers from temporal...
arXiv:2412.01090v3 Announce Type: replace Abstract: Video depth estimation is essential for applications such as autonomous driving, AR/VR, and robotics. Recent transformer-based single-image monocul...
arXiv:2609.09394v1 Announce Type: new Abstract: Recovering metric 3D geometry from monocular images is a fundamental computer vision task, yet current methods remain heavily fragmented by fixed camer...
arXiv:2605.23889v2 Announce Type: replace Abstract: Online 3D reconstruction requires estimating camera pose and scene geometry under strict causal and bounded-memory constraints. Existing methods of...
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.
Forge4D is a feed‑forward model that reconstructs temporally aligned 4D human representations from uncalibrated sparse‑view videos, enabling both novel view and novel time synthesis. It achieves this by jointly streaming 3D Gaussian reconstruction with dense motion prediction, using learnable state tokens for temporal consistency and a self‑supervised retargeting loss for motion prediction. Extensive experiments confirm its effectiveness on in‑domain and out‑of‑domain datasets.
arXiv:2610.08780v1 Announce Type: cross Abstract: World models offer a data-driven alternative to traditional simulators for robotics, with applications spanning policy evaluation, improvement, and p...
The paper proposes a new sequence-to-sequence formulation for multi-view stereo (MVS) that jointly predicts 3D geometry for all input views using a global transformer architecture. It introduces ray‑map embeddings to inject camera parameters into image tokens and a unified global cost volume to capture 3D structure across all views. Experiments on public benchmarks demonstrate state‑of‑the‑art performance, outperforming both traditional MVS and feed‑forward reconstruction baselines.