arXiv:2602. 19710v3 Announce Type: replace-cross Abstract: Existing Vision-Language-Action (VLA) models often suffer from feature collapse and low training efficiency because they entangle high-level perception with sparse, embodiment-specific action supervision.
arXiv:2607. 02417v1 Announce Type: cross Abstract: Autonomous robots often need to move their camera before they can act: to inspect an object, reveal an occluded region, or obtain a view that responds to a user's intent.
arXiv:2608.22039v1 Announce Type: new Abstract: Structure-from-Motion (SfM) is a cornerstone of 3D perception, yet current methods often fail when applied to complex videos involving challenging came...
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:2609.01252v1 Announce Type: new Abstract: In camera-controlled video generation, geometry-aware positional encodings condition tokens on camera extrinsics and per-token viewing rays. Existing s...
Object-Uni is a unified model that integrates pose perception, spatial reasoning, pose-conditioned generation, and novel view synthesis for object-centric spatial understanding and controllable image generation. It treats object pose as an explicit geometric variable shared across tasks and introduces a viewpoint-based orientation abstraction to make pose interpretable by multimodal large language models. The authors also create a new benchmark, UniSpatial-80K, and demonstrate that Object‑Uni improves both pose understanding and pose‑controllable generation compared to existing models.
MINT is a foundation model that directly predicts world-space two-hand trajectories from egocentric RGB video, jointly estimating camera motion, hand states, and hand presence in a single spatiotemporal representation. It uses an open-source labeling pipeline, EGOPIPELINE, to generate large-scale pseudo-labels for pretraining, followed by fine-tuning on a small set of high-quality joint annotations. The model outperforms existing multi-stage approaches in accuracy and speed, and generalizes zero‑shot to unseen egocentric datasets.
VersaCamVLA introduces a camera‑configurable framework that separates camera‑set representation from action learning in Vision‑Language‑Action models. It learns a unified scene‑token interface that maps any number of posed RGB views into fixed‑size latent tokens using multi‑signal target‑view prediction and Wrist‑Augmented Pose Sampling. At deployment, a lightweight spatial encoder injects these tokens into a pretrained VLA, enabling robust manipulation without explicit 3D sensing or novel‑view rendering, and consistently outperforms prior methods across varying camera counts and unseen poses.
arXiv:2608.30342v1 Announce Type: new Abstract: 3D Gaussian Splatting (3DGS) enables photorealistic real-time novel view synthesis, yet placing a virtual camera to capture a desired frame remains lar...
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.
arXiv:2609.13733v1 Announce Type: new Abstract: Stable and reliable 4D spatial understanding is fundamental for autonomous driving systems. While feedforward reconstruction networks can estimate came...
The paper introduces ORMOT, a new task that extends Referring Multi‑Object Tracking to omnidirectional 360° imagery, ensuring full scene context for language‑guided tracking. It presents ORSet, a dataset of 27 omnidirectional scenes with 848 language descriptions and 3,401 annotated objects, and introduces ORTrack, an LVLM‑driven framework that performs zero‑shot detection and robust cross‑frame association. Experiments on ORSet show that ORTrack achieves state‑of‑the‑art performance, establishing a strong baseline for future research.