activity
20242026
collaborators
Showing cs.CVShow all

20 papers · 1 filter

cs.CV2026

Chain of Spatial Thoughts: Modality-Agnostic Spatial Grounding for Vision Language Models

Hunter Schofield, Mohammed Elmahgiubi, Mohammad Mahdavian +4

Spatial understanding is fundamental to embodied intelligence, underpinning applications such as robotic manipulation, embodied navigation, and autonomous driving. Although recent…

cs.CV2026

TurboVGGT: Fast Visual Geometry Reconstruction with Adaptive Alternating Attention

David Huang, Guile Wu, Chengjie Huang +2

Recent feed-forward 3D reconstruction methods, such as visual geometry transformers, have substantially advanced the traditional per-scene optimization paradigm by enabling effecti…

cs.CV2026

MoVieDrive: Urban Scene Synthesis with Multi-Modal Multi-View Video Diffusion Transformer

Guile Wu, David Huang, Dongfeng Bai +1

Urban scene synthesis with video generation models has recently shown great potential for autonomous driving. Existing video generation approaches to autonomous driving primarily f…

cs.CV2026

Spatial4D-Bench: A Versatile 4D Spatial Intelligence Benchmark

Pan Wang, Yang Liu, Guile Wu +23

4D spatial intelligence involves perceiving and processing how objects move or change over time. Humans naturally possess 4D spatial intelligence, supporting a broad spectrum of sp…

cs.CV2026

UniScale: Unified Scale-Aware 3D Reconstruction for Multi-View Understanding via Prior Injection for Robotic Perception

Mohammad Mahdavian, Gordon Tan, Binbin Xu +3

We present UniScale, a unified, scale-aware multi-view 3D reconstruction framework for robotic applications that flexibly integrates geometric priors through a modular, semanticall…

cs.CV2026

Language and Geometry Grounded Sparse Voxel Representations for Holistic Scene Understanding

Guile Wu, David Huang, Bingbing Liu +1

Existing 3D open-vocabulary scene understanding methods mostly emphasize distilling language features from 2D foundation models into 3D feature fields, but largely overlook the syn…