ROSETTA is a training‑free calibration layer that aligns feature spaces from independently trained encoders by estimating a local rotation in whitened space. It relies on the observation that the relative transformation between any two such systems is a spatially preserving rotation whose angular velocity behaves like white noise, and that the cross‑covariance between encoder outputs has low effective rank, making local alignment tractable. The method uses an expectation‑maximization procedure and requires no co‑observation at query time, achieving milliseconds overhead per query on three public driving datasets across LiDAR, camera, thermal, and event modalities.
Vision Foundation Models (VFMs) have significantly advanced dense feature matching, yet severe in-plane rotation remains a critical challenge. Existing solutions face a fundamental dilemma: data-driven methods require inefficient parameter scaling to implicitly learn rotations, whereas strictly equivariant networks lack the semantic capacity of modern VFMs.
GINIO is a geometric SO(3)-equivariant interface designed for neural inertial odometry that ensures learned measurements transform consistently under any IMU mounting convention. It predicts motion measurements and uncertainties that obey vector and tensor transformation laws, and introduces Last-Frame Alignment to enable efficient sensor-frame learning equivalent to world-frame training. The interface is instantiated in several architectures—filter-connected NIO, AirIO-style recurrent aerial prediction, EqNIO-style full-SO(3) canonicalization, and ResNet-style temporal backbones—achieving significant accuracy and efficiency gains across multiple benchmarks.
arXiv:2606. 17961v1 Announce Type: cross Abstract: Positional encoding is a fundamental component of Transformer architectures, as it injects information about the spatial or sequential arrangement of inputs.
arXiv:2608.27971v1 Announce Type: new Abstract: Unmanned aerial vehicle (UAV) multimodal perception integrates visible (RGB), infrared (IR), synthetic aperture radar (SAR), and depth sensors for scen...
PAGER is a label‑free adaptation method that aligns partial, viewpoint‑dependent 3D observations with a frozen global semantic space. It uses matched‑point feature alignment and relational supervision to anchor partial features to their global counterparts while preserving similarity structure, all without altering the pretrained encoder or global probe. Experiments show PAGER outperforms label‑supervised PEFT on Sonata and Concerto, and achieves superior zero‑shot transfer from ScanNet to ScanNet++ compared to fully fine‑tuned Sonata.
The paper introduces TSDA-Track, a Template-Search Domain Adaptation framework designed to reduce modality gaps in cross‑modal visual object tracking. Two variants are explored: Pre‑AFA TSDA‑Track uses adversarial alignment before transformer interaction, while Enc‑CFA TSDA‑Track applies contrastive alignment after interaction to strengthen cross‑modal correspondence. Experiments on datasets such as LasHeR, RGBT234, GTOT, and Anti‑UAV‑024 show that both variants outperform state‑of‑the‑art trackers, with Pre‑AFA achieving an SR/PR of 43.2/56.0 on RGBT234 under the modality‑switch protocol.
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:2601.13913v3 Announce Type: replace Abstract: We consider monocular 3D human pose estimation (HPE), where the goal is to predict 3D human skeletal joints from a single 2D image, typically via 2...
RoLaQ is an offline technique that jointly calibrates rotation and quantization range for 2‑bit key‑value caches in multi‑head latent attention models. By refining a shared rotation within subspaces defined by frozen key and value projections and learning coupled quantization thresholds and reconstruction gains, RoLaQ improves prediction matching and attention‑output supervision while keeping model weights frozen. Experiments on three MLA models and six benchmarks show that RoLaQ outperforms other 2‑bit methods, achieving higher average accuracy and, in a DeepSeek‑V2‑Lite implementation, nearly four times the BF16 KV capacity and more than double the decode throughput for 256K input tokens.
arXiv:2606. 31585v1 Announce Type: cross Abstract: The remarkable scalability of Transformers has expanded their application to 3D computer vision, where camera-aware positional encoding is crucial for providing spatial cues in multi-view geometry.
The paper presents a new monocular spacecraft pose estimation model that achieves the lowest reported mean rotation errors on the SPEED+ lightbox and sunlamp test sets. By replacing smaller encoders with a large self‑supervised ViT foundation model (DINOv3) and scaling up to 840 M parameters, the authors improve accuracy from 300 M to 840 M parameters without saturation. The 840 M model also runs on a Jetson Orin NX 16 GB with 133.8 ms per crop and 32.0 W power draw, demonstrating embedded inference feasibility while training solely on synthetic data.
arXiv:2610.33356v1 Announce Type: new Abstract: Event cameras provide microsecond temporal resolution, high dynamic range, and sparse asynchronous measurements, making them compelling for odometry un...