287 citations · 506 across the 42 of their papers we have counts for
45 papers
Decoupling Spherical Reasoning from Dense Prediction for 360 Depth Estimation
Zhijie Shen, Chunyu Lin, Shuai Zheng +4
The equirectangular projection (ERP) is widely used for panoramic depth estimation, but its spatially varying distortion makes geometry-consistent feature modeling challenging. We…
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…
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…
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…
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…
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…
Advancing Real-World Parking Slot Detection with Large-Scale Dataset and Semi-Supervised Baseline
Zhihao Zhang, Chunyu Lin, Lang Nie +2
As automatic parking systems evolve, the accurate detection of parking slots has become increasingly critical. This study focuses on parking slot detection using surround-view came…
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…
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…
StabStitch++: Unsupervised Online Video Stitching with Spatiotemporal Bidirectional Warps
Lang Nie, Chunyu Lin, Kang Liao +3
We retarget video stitching to an emerging issue, named warping shake, which unveils the temporal content shakes induced by sequentially unsmooth warps when extending image stitchi…
You Need a Transition Plane: Bridging Continuous Panoramic 3D Reconstruction with Perspective Gaussian Splatting
Zhijie Shen, Chunyu Lin, Shujuan Huang +3
Recently, reconstructing scenes from a single panoramic image using advanced 3D Gaussian Splatting (3DGS) techniques has attracted growing interest. Panoramic images offer a 360$\t…
Beyond Wide-Angle Images: Structure-to-Detail Video Portrait Correction via Unsupervised Spatiotemporal Adaptation
Wenbo Nie, Lang Nie, Chunyu Lin +4
Wide-angle cameras, despite their popularity for content creation, suffer from distortion-induced facial stretching-especially at the edge of the lens-which degrades visual appeal.…
Semi-Supervised 360 Layout Estimation with Panoramic Collaborative Perturbations
Junsong Zhang, Chunyu Lin, Zhijie Shen +3
The performance of existing supervised layout estimation methods heavily relies on the quality of data annotations. However, obtaining large-scale and high-quality datasets remains…
Jasmine: Harnessing Diffusion Prior for Self-supervised Depth Estimation
Jiyuan Wang, Chunyu Lin, Cheng Guan +5
In this paper, we propose Jasmine, the first Stable Diffusion (SD)-based self-supervised framework for monocular depth estimation, which effectively harnesses SD's visual priors to…
What Really Matters for Learning-based LiDAR-Camera Calibration
Shujuan Huang, Chunyu Lin, Yao Zhao
Calibration is an essential prerequisite for the accurate data fusion of LiDAR and camera sensors. Traditional calibration techniques often require specific targets or suitable sce…
Revisiting Monocular 3D Object Detection with Depth Thickness Field
Qiude Zhang, Chunyu Lin, Zhijie Shen +2
Monocular 3D object detection is challenging due to the lack of accurate depth. However, existing depth-assisted solutions still exhibit inferior performance, whose reason is unive…
Str-L Pose: Integrating Point and Structured Line for Relative Pose Estimation in Dual-Graph
Zherong Zhang, Chunyu Lin, Shujuan Huang +2
Relative pose estimation is crucial for various computer vision applications, including Robotic and Autonomous Driving. Current methods primarily depend on selecting and matching f…
Revisiting 360 Depth Estimation with PanoGabor: A New Fusion Perspective
Zhijie Shen, Chunyu Lin, Lang Nie +3
Depth estimation from a monocular 360 image is important to the perception of the entire 3D environment. However, the inherent distortion and large field of view (FoV) in 360 image…
SGFormer: Spherical Geometry Transformer for 360 Depth Estimation
Junsong Zhang, Zisong Chen, Chunyu Lin +5
Panoramic distortion poses a significant challenge in 360 depth estimation, particularly pronounced at the north and south poles. Existing methods either adopt a bi-projection fusi…
Digging into contrastive learning for robust depth estimation with diffusion models
Jiyuan Wang, Chunyu Lin, Lang Nie +3
Recently, diffusion-based depth estimation methods have drawn widespread attention due to their elegant denoising patterns and promising performance. However, they are typically un…
Eliminating Warping Shakes for Unsupervised Online Video Stitching
Lang Nie, Chunyu Lin, Kang Liao +4
In this paper, we retarget video stitching to an emerging issue, named warping shake, when extending image stitching to video stitching. It unveils the temporal instability of warp…
Semi-Supervised Coupled Thin-Plate Spline Model for Rotation Correction and Beyond
Lang Nie, Chunyu Lin, Kang Liao +2
Thin-plate spline (TPS) is a principal warp that allows for representing elastic, nonlinear transformation with control point motions. With the increase of control points, the warp…
Camera calibration for the surround-view system: a benchmark and dataset
L Qin, C Lin, S Huang +2
Surround-view system (SVS) is widely used in the Advanced Driver Assistance System (ADAS). SVS uses four fisheye lenses to monitor real-time scenes around the vehicle. However, acc…