arXiv Computer Vision
Learning the 4D World through Point Trajectory Forecasting
Read the original on arXiv Computer Vision →The Flow has not summarised this story yet — read it at arXiv Computer Vision.
Related stories
arXiv Computer Vision
3d ago
MolmoMotion: Forecasting Point Trajectories in 3D with Language Instruction
arXiv:2606.18558v2 Announce Type: replace Abstract: Motion forecasting is central to visual intelligence: agents must anticipate how objects will move in order to plan actions, reason about physical...
arXiv Computer Vision
Sep 17
PointZero: 3D Point Track Completion for Learning Transferable 3D Dynamics
arXiv:2609.19142v1 Announce Type: new Abstract: World models endow perceptual systems with the ability to predict how scenes evolve under interaction. They are most beneficial when trained on diverse...
Hugging Face Trending Papers
Sep 16
PointZero: 3D Point Track Completion for Learning Transferable 3D Dynamics
World models endow perceptual systems with the ability to predict how scenes evolve under interaction. They are most beneficial when trained on diverse volumes of data, to instill a rich prior into do...
arXiv Machine Learning
Jun 4
PointAction: 3D Points as Universal Action Representations for Robot Control
arXiv:2606. 03943v1 Announce Type: cross Abstract: Video-Action Models (VAMs) leverage the broad visual dynamics captured by pre-trained video diffusion models, offering a promising path toward generalizable robot manipulation.
arXiv Computer Vision
Sep 3
Spatially Aware World Action Model via Geometric Latent Diffusion
The paper introduces Spatially Aware World Action Model (SA‑WAM), a diffusion‑based framework that extends existing World Action Models by incorporating depth information alongside RGB to enable 3‑D‑aware action and future‑state prediction. SA‑WAM repurposes a pretrained video diffusion model, using a nonlinear encoding to map unbounded depth into the tokenizer’s bounded domain, thus preserving pretrained visual priors without 3‑D‑specific fine‑tuning. The model achieves state‑of‑the‑art performance on RoboCasa and LIBERO‑Plus benchmarks and demonstrates superior real‑world performance on a UR5 robotic arm in randomized environments, while also providing analysis linking world‑model prediction quality to rollout success.
arXiv Computer Vision
Sep 16
Mem-World: Memory-Augmented Action-Conditioned World Models for Persistent Robot Manipulation
Mem-World introduces a memory‑augmented action‑conditioned world model for robot manipulation, featuring W‑VMem—a 4D wrist‑view‑centered surfel‑indexed memory that anchors historical observations to evolving surface elements. By explicitly modeling when and where scene elements are observed, the system retrieves geometry‑aware history frames during generation, providing informative, non‑redundant context for future action predictions. Experiments demonstrate that Mem‑World produces persistent rollouts, improves policy evaluation reliability (14.5 % higher Pearson correlation with real‑world performance), and boosts long‑horizon task success rates from 58 % to 72 % using synthetic data generation.