Driving by the Rules: A Benchmark for Integrating Traffic Sign Regulations into Vectorized HD Map
Comments 26 pages, 16 figures. Accepted as a Highlight at CVPR 2025. Project page: https://miv-xjtu.github.io/MapDR/
期刊&会议
CVPR
Conference on Computer Vision and Pattern Recognition · 会议 · Computer Vision
KnobGen: Controlling the Sophistication of Artwork in Sketch-Based Diffusion Models
Comments Accepted to CVPR 2025 Workshop on CVEU
Neural Motion Simulator: Pushing the Limit of World Models in Reinforcement Learning
Comments 8 pages (main), 2-page appendix, 8 figures, accepted by CVPR 2025
Glossy Object Reconstruction with Cost-effective Polarized Acquisition
Comments Accepted to CVPR 2025 as highlight
Wheat3DGS: In-field 3D Reconstruction, Instance Segmentation and Phenotyping of Wheat Heads with Gaussian Splatting
Comments Copyright 2025 IEEE. This is the author's version of the work. It is posted here for your personal use. Not for redistribution. The definitive version is published in the 2025 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW)
EIDT-V: Exploiting Intersections in Diffusion Trajectories for Model-Agnostic, Zero-Shot, Training-Free Text-to-Video Generation
Comments Accepted at IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) 2025
Domain Generalization through Attenuation of Domain-Specific Information
Comments Accepted by CVPR 2025 Workshops
Masked Scene Modeling: Narrowing the Gap Between Supervised and Self-Supervised Learning in 3D Scene Understanding
Comments Accepted at CVPR 2025
PosterMaker: Towards High-Quality Product Poster Generation with Accurate Text Rendering
Comments Accepted by CVPR 2025. Project Page: https://poster-maker.github.io
SemiDAViL: Semi-supervised Domain Adaptation with Vision-Language Guidance for Semantic Segmentation
Comments Accepted at CVPR 2025
Mesh Mamba: A Unified State Space Model for Saliency Prediction in Non-Textured and Textured Meshes
Comments to be published in CVPR 2025
Automated Generation of Challenging Multiple-Choice Questions for Vision Language Model Evaluation
Comments CVPR 2025
DCSEG: Decoupled 3D Open-Set Segmentation using Gaussian Splatting
Comments To be published in CVPR Workshop on Open-World 3D Scene Understanding with Foundation Models
Design2GarmentCode: Turning Design Concepts to Tangible Garments Through Program Synthesis
Comments The IEEE/CVF Conference on Computer Vision and Pattern Recognition (2025)
GigaHands: A Massive Annotated Dataset of Bimanual Hand Activities
Comments CVPR 2025 Highlight
EchoONE: Segmenting Multiple echocardiography Planes in One Model
Comments Accepted by CVPR 2025
FedSECA: Sign Election and Coordinate-wise Aggregation of Gradients for Byzantine Tolerant Federated Learning
Comments Accepted in 4th Workshop on Federated Learning for Computer Vision (FedVision-2025), held in conjunction with CVPR-2025
Boost Your Human Image Generation Model via Direct Preference Optimization
Comments Accepted to CVPR 2025 as a highlight paper
From Broadcast to Minimap: Achieving State-of-the-Art SoccerNet Game State Reconstruction
Comments Accepted for presentation at the CVPR 2025 CVsports Workshop
HiMoR: Monocular Deformable Gaussian Reconstruction with Hierarchical Motion Representation
Comments CVPR 2025. Project Page: https://pfnet-research.github.io/himor
A Large-Scale Analysis on Contextual Self-Supervised Video Representation Learning
Comments CVPR'25 Workshop: 6th Data-Efficient Workshop
Hyperbolic Category Discovery
Comments Accepted as a conference paper at CVPR 2025
Temporal Alignment-Free Video Matching for Few-shot Action Recognition
Comments 10 pages, 7 figures, 6 tables, Accepted to CVPR 2025 as Oral Presentation
SVLTA: Benchmarking Vision-Language Temporal Alignment via Synthetic Video Situation
Comments CVPR 2025. The first two authors contributed equally
PRIMEDrive-CoT: A Precognitive Chain-of-Thought Framework for Uncertainty-Aware Object Interaction in Driving Scene Scenario
Comments Accepted at The IEEE/CVF Conference on Computer Vision and Pattern Recognition 2025 - CVPRW
Leveraging Synthetic Adult Datasets for Unsupervised Infant Pose Estimation
Comments Accepted at ABAW@CVPR 2025
SoundVista: Novel-View Ambient Sound Synthesis via Visual-Acoustic Binding
Comments Highlight Accepted to CVPR 2025
PartStickers: Generating Parts of Objects for Rapid Prototyping
Comments Accepted to CVPR CVEU workshop 2025
Few-shot Personalized Scanpath Prediction
Comments Accepted by CVPR 2025,20 pages, 10 figures
Taxonomy-Aware Evaluation of Vision-Language Models
Comments CVPR 2025
