The paper introduces a biologically inspired framework that learns object‑centric visual representations from raw videos without human annotations or camera calibration. By using motion boundaries detected via optical flow and clustering to create pseudo‑instance masks, the method supervises a single‑image encoder with pixel‑level pairwise metric learning. Training on 195 million pseudo‑labeled frames and expanding to 421 million frames through Motion‑Verified Self‑Training, the approach yields Swin‑based encoders that outperform or match supervised and self‑supervised baselines on tasks such as monocular depth estimation, 3D object detection, 3D occupancy prediction, and end‑to‑end planning.
arXiv:2609.39785v1 Announce Type: new Abstract: The Segment Anything Model (SAM) relies heavily on massive manual annotations, creating a fundamental bottleneck for model scaling. While unsupervised...
arXiv:2608.13147v2 Announce Type: replace Abstract: Camera-based autonomous driving perception requires a shared representation that preserves metric 3D structure across synchronized multi-camera str...
Real-world spatial intelligence requires agents to understand scenes from continuous video streams, where objects move, persist, disappear, and reappear over time. While recent spatial foundation models have enabled generalizable feed-forward 3D reconstruction, most streaming methods remain geometry-centric and lack temporally consistent object-level understanding.
arXiv:2605.13018v2 Announce Type: replace Abstract: Object-centric scene understanding is a fundamental challenge in computer vision. Existing approaches often rely on multi-stage pipelines that firs...
arXiv:2503. 19947v2 Announce Type: replace-cross Abstract: Generalized metric depth understanding is critical for precise vision-guided robotics, which current state-of-the-art (SOTA) vision-encoders do not support.
arXiv:2604.09045v2 Announce Type: replace Abstract: Recent works on 3D scene understanding leverage 2D masks from visual foundation models (VFMs) to supervise radiance fields, enabling instance-level...
arXiv:2608.21136v1 Announce Type: new Abstract: Recently, open-vocabulary zero-shot 3D scene understanding using vision foundation models has emerged as a promising alternative to data-intensive supe...
MoSE3 is a feed‑forward model that predicts dense SE(3) motion—full 6‑DoF rigid transforms—at every pixel from monocular RGB video, providing rotation, translation, and grouping information simultaneously. It achieves this by jointly learning 3D point tracks and rigidity embeddings, then differentiably fitting transforms within soft rigid clusters. The authors also release Art‑Kubric, a large synthetic dataset with dense SE(3) and rigidity labels, and demonstrate state‑of‑the‑art performance on both rigid and articulated benchmarks, with strong generalization to real‑world videos.
PURE is an unlabeled post‑training refinement framework that enhances feed‑forward 3D reconstruction models by improving depth and camera estimation without ground‑truth supervision. It distills structural knowledge from state‑of‑the‑art 2D priors into 4D architectures, using relative depth constraints, affine‑invariant geometry distillation, and pose refinement via feature correspondences. Experiments on synthetic and real‑world dynamic benchmarks show consistent improvements across multiple state‑of‑the‑art models, effectively mitigating domain shifts and unlocking their architectural limits in challenging in‑the‑wild scenes.
Video object segmentation (VOS) is a fundamental task in video understanding, requiring accurate delineation and consistent tracking of objects across frames. While supervised methods achieve strong performance, they rely on densely annotated datasets that are costly to obtain and have limited domain coverage.
arXiv:2610.31640v1 Announce Type: new Abstract: Video diffusion models have learned rich 3D/4D priors, making them promising for scene generation and video re-rendering. However, their use in spatial...
arXiv:2506.17545v2 Announce Type: replace Abstract: Large language models are increasingly being applied to 3D scene understanding. However, existing 3D-aware LLMs largely operate as black boxes: the...