works on

From the 2 of 64 linked papers with an AI index.

activity
20242026
collaborators
Showing cs.CVShow all

65 papers · 1 filter

cs.CV2026

SpatialDiff: 3D-Aware Object Movement via Implicit Spatial Modeling

Zheng Liu, Zijian He, Huiguo He +5

Recent advances in image editing allow impressive manipulation of objects, existing methods still struggle to handle spatial movement in complex scenes, such as objects span differ…

cs.CV2026

MoRoute: Dynamic Routing for In-Context Multimodal Video Generation

Chong Gao, Jie Ma, Zhan Peng +5

Multimodal video generation aims to generate and edit videos conditioned on arbitrary combinations of text, images, and videos within a single model, allowing diverse tasks to shar…

cs.CV2026

AdaAnchor4D: Anchor-Conditioned Spatiotemporal Feature Aggregation for Monocular UAV 4D Reconstruction

Peiyi Xu, Junpeng Zhang, Guanbin Li +6

The paper introduces AdaAnchor4D, a method that uses adaptive anchor-based feature aggregation to improve monocular UAV video reconstruction of dynamic urban scenes, reducing artif…

cs.CV2026

ARDepth: Auto-regressive Monocular Depth Estimation with Progressive Visual Conditioning

Zijie Wang, Wei Zhang, Weiming Zhang +4

ARDepth proposes an auto-regressive approach to monocular depth estimation that builds depth maps progressively across increasing spatial resolutions, using scale‑progressive condi…

cs.CV2026

DreamShot: Personalized Storyboard Synthesis with Video Diffusion Prior

Junjia Huang, Binbin Yang, Pengxiang Yan +6

Storyboard synthesis plays a crucial role in visual storytelling, aiming to generate coherent shot sequences that visually narrate cinematic events with consistent characters, scen…

cs.CV2026

PhyScene3D: Physically Consistent Interactive 3D Tabletop Scene Generation

Weixing Chen, Zhuoqian Feng, Yang Liu +6

Generating physically consistent 3D tabletop scenes is a fundamental yet underexplored problem for interactive and generalist robotic learning. The challenge stems from dense objec…