← Back to all news
arXiv Computer Vision By Xiaoyi Liu, Hao Tang

Geometry-Centered 3D Latent World Models for Growing Surfaces

Read the original on arXiv Computer Vision →

The paper introduces FOLIAGE, a geometry‑centered latent world model designed for systems that grow and change shape over time. FOLIAGE allocates higher‑resolution state to regions expected to grow while keeping mature areas compact, fusing RGB, point‑cloud, and mesh data into a deployable geometric state and conditioning dynamics on material controls. The authors evaluate the model on new benchmarks (SURF‑GARDEN and SURF‑BENCH) and demonstrate significant reductions in inverse‑material error, mesh forecasting error, and improved cross‑modal retrieval, with robust performance under sensor loss and correspondence corruption.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv Computer Vision.

Related stories

arXiv AI
Jul 1

LeCropFollow: Latent Space Planning for Navigation in Unstructured Crop Fields

arXiv:2606. 31941v1 Announce Type: cross Abstract: Unstructured navigational features, such as irregular planting or discontinuities, remain the primary failure mode for under-canopy agricultural robots.

By Felipe Tommaselli, Francisco Affonso, Arthur Pompeu, Gianluca Capezzuto, Arun Narenthiran Sivakumar, Girish Chowdhary, Marcelo Becker
diffusionreinforcement-learningroboticsfine-tuningbenchmarks
More like this →
arXiv Computer Vision
Oct 16

PiCo: Physics-Informed Concept Probing for Geo-Foundation Models

PiCo is a post‑hoc framework that explains Geo‑foundation model predictions by identifying concept vectors in the model’s embedding space. It generates synthetic multispectral satellite data using a 3D radiative transfer model and a game engine to reveal physical sensitivities, then projects embeddings onto these vectors to quantify concept importance. Evaluations on three GFMs show that PiCo can recover most of the full‑embedding accuracy and uncover how different physical concepts influence predictions for tasks such as ground‑cover estimation and forest classification.

By Yihang She, Andrew Blake, Jianbo Qi, Srinivasan Keshav
rag
More like this →
arXiv Machine Learning
Aug 7

SR-JEPA: Learning Predictive Latent State in 3D Scenes

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.

By Zihan Zhou, Qifu Wen, Xi Zeng
rag
More like this →