16 papers
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…
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…
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…
From Editor to Dense Geometry Estimator
JiYuan Wang, Chunyu Lin, Lei Sun +5
Leveraging visual priors from pre-trained text-to-image (T2I) generative models has shown success in dense prediction. However, dense prediction is inherently an image-to-image tas…
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…
Robust Image Stitching with Optimal Plane
Lang Nie, Yuan Mei, Kang Liao +3
We present \textit{RopStitch}, an unsupervised deep image stitching framework with both robustness and naturalness. To ensure the robustness of \textit{RopStitch}, we propose to in…