arXiv:2608. 05774v1 Announce Type: cross Abstract: Joint-embedding predictive architectures learn by predicting latent representations of missing observations, yet many masked JEPAs are evaluated primarily through the encoders they produce.
arXiv:2608.29434v1 Announce Type: cross Abstract: JEPA world models make latent-space planning a practical route to control, but they are built almost exclusively on images. Whether latent prediction...
arXiv:2607. 00514v1 Announce Type: cross Abstract: Automatic understanding of dynamic 4D point clouds, the 3D-point sequences captured over time by depth sensors and LiDAR, is central to robotics and embodied perception.
PGL-3D introduces a progressive geometric learning framework for 3D visual query localization, where intermediate cuboids guide feature aggregation and refinement. The method predicts a complete cuboid for each proposal, selects reference observations via Query‑Tube‑Memory, pools query‑conditioned features, and re‑predicts refined cuboids. A training‑only objective, ST‑D9O, supervises cuboid geometry at every stage, yielding significant performance gains over prior baselines.
arXiv:2605.26949v2 Announce Type: replace Abstract: 3D shape completion from partial scans remains challenging for unseen categories and noisy real-world observations, where geometry alone is often i...
arXiv:2609.31595v1 Announce Type: new Abstract: 3D scene graphs provide a structured representation of complex environments by encoding objects, their semantic attributes, and the spatial and functio...
arXiv:2608.24093v1 Announce Type: cross Abstract: Self-supervised representation learning for 4D point cloud videos is challenging because annotations are costly and reconstruction-based pretraining...
GoDeep is an annotation‑free method for open‑vocabulary 3D scene understanding that uses a vision‑language model solely as a translator to generate structured, entity‑level descriptions of each image. These descriptions are projected and aggregated in a language‑only embedding space, eliminating the need for a 3D training corpus or domain‑specific encoder. The approach achieves competitive performance on ScanNet++ and a cultural heritage benchmark, accurately localizes out‑of‑vocabulary objects, and offers explainable, point‑level predictions.
Subspace-Decomposed JEPAs (SD-JEPA) split the latent space of Joint-Embedding Predictive Architectures into two orthogonal subspaces: a low-dimensional progression subspace trained with a cosine-margin triplet loss and a high-dimensional content subspace regularised by SIGReg. The authors prove that the anti-collapse forces act on disjoint coordinates, allowing additive composition rather than competition. SD-JEPA outperforms the LeWM baseline on most control benchmarks and the strongest non-LeWM JEPA baseline on Push‑T, with a subspace-ablation confirming the split as essential. The 1‑D angular progression coordinate serves as a scene-aware compass, advancing with task progress, regressing on backtracking, and relocalising under perturbations to separate surprise from meaning.
arXiv:2609.01530v1 Announce Type: new Abstract: Self-supervised pre-training via cross-view completion learns strong features for 3D vision from co-visible regions of image pairs. However, the refere...
arXiv:2609.09507v1 Announce Type: new Abstract: Learned image matching has experienced significant progress in recent years, culminating in robust and accurate matchers such as RoMa, whose robustness...
The paper introduces the Geometry‑Native Autoencoder (GAE), a compact latent space that can be decoded into appearance, depth, camera parameters, and point maps, enabling 3D‑consistent world generation. By reparameterizing a geometry foundation model’s features, GAE replaces traditional appearance‑centric latents and improves visual quality and 3D coherence, achieving significant reductions in FVD and camera‑trajectory error on benchmark datasets. The work demonstrates that a geometry‑native latent space can serve as a shared interface between perception and generation models.
arXiv:2609.23404v1 Announce Type: new Abstract: Point cloud completion aims to infer a complete 3D shape from a partial point cloud and serves as a fundamental building block for downstream tasks suc...