works on

From the 1 of 6 linked papers with an AI index.

collaborators

6 papers

cs.CV2026

CinemaTraj: Composing Atomic Camera Trajectories for 3D Scenes with LLM Agents

Qianru Li, Xuyang Chen, Erkin Türköz +5

CinemaTraj generates cinematic camera movements in 3D environments from natural language prompts by using an LLM agent that reasons over a structured 3D scene graph and produces co…

cs.CV2026

HierLoc: Hyperbolic Entity Embeddings for Hierarchical Visual Geolocation

Hari Krishna Gadi, Daniel Matos, Hongyi Luo +4

Visual geolocalization, the task of predicting where an image was taken, remains challenging due to global scale, visual ambiguity, and the inherently hierarchical structure of geo…

cs.CV2026

Driving with DINO: Vision Foundation Features as a Unified Bridge for Sim-to-Real Generation in Autonomous Driving

Xuyang Chen, Conglang Zhang, Chuanheng Fu +10

Driven by the emergence of Controllable Video Diffusion, existing Sim2Real methods for autonomous driving video generation typically rely on explicit intermediate representations t…

cs.CV2026

MeSS: City Mesh-Guided Outdoor Scene Generation with Cross-View Consistent Diffusion

Xuyang Chen, Zhijun Zhai, Kaixuan Zhou +9

Mesh models have become increasingly accessible for numerous cities; however, the lack of realistic textures restricts their application in virtual urban navigation and autonomous…

cs.LG2025

TurnBack: A Geospatial Route Cognition Benchmark for Large Language Models through Reverse Route

Hongyi Luo, Qing Cheng, Daniel Matos +7

Humans can interpret geospatial information through natural language, while the geospatial cognition capabilities of Large Language Models (LLMs) remain underexplored. Prior resear…

cs.CV2025

Box2Poly: Memory-Efficient Polygon Prediction of Arbitrarily Shaped and Rotated Text

Xuyang Chen, Dong Wang, Konrad Schindler +4

Recently, Transformer-based text detection techniques have sought to predict polygons by encoding the coordinates of individual boundary vertices using distinct query features. How…