activity
20202026
most citedUnsupervised Deep Image Stitching: Reconstructing Stitched Features to Images

287 citations · 344 across the 20 of their papers we have counts for

collaborators
Showing cs.CVShow all

33 papers · 1 filter

cs.CV2026

SphereSOD: Geometry-Structure Coupled Learning for 360 Salient Object Detection

Junsong Zhang, Zhijie Shen, Shuai Zheng +4

360° salient object detection (SOD) aims to accurately segment salient regions across a full field of view. However, equirectangular projection (ERP) introduces severe spatial dist…

cs.CV2026

Puffin-World: Scaling a Unified Multimodal Model with Native 3D World States

Kang Liao, Yihang Luo, Xiao-Ming Wu +7

We propose Puffin-World, a unified multimodal architecture that integrates physical understanding, spatial simulation, and 3D world generation and reconstruction without relying on…

cs.CV2026

CaC: Advancing Video Reward Models via Hierarchical Spatiotemporal Concentrating

Jiyuan Wang, Huan Ouyang, Jiuzhou Lin +15

In this paper, we propose Concentrate and Concentrate (CaC), a coarse-to-fine anomaly reward model based on Vision-Language Models. During inference, it first conducts a global tem…

cs.CV2026

UniStitch: Unifying Semantic and Geometric Features for Image Stitching

Yuan Mei, Lang Nie, Kang Liao +3

Traditional image stitching methods estimate warps from hand-crafted geometric features, whereas recent learning-based solutions leverage semantic features from neural networks ins…

cs.CV2026

RePer-360: Releasing Perspective Priors for 360 Depth Estimation via Self-Modulation

Cheng Guan, Chunyu Lin, Zhijie Shen +2

Recent depth foundation models trained on perspective imagery achieve strong performance, yet generalize poorly to 360 images due to the substantial geometric discrepancy b…

cs.CV2026

Edit in 2D, Verify in 3D: Reinforcement Learning for Multi-view Consistent Scene Editing

Jiyuan Wang, Chunyu Lin, Lei Sun +8

Leveraging the priors of 2D diffusion models for 3D editing has emerged as a promising paradigm. However, multi-view consistency remains challenging in edited results, and the extr…