Decompositional Neural Scene Reconstruction with Generative Diffusion Prior
Comments CVPR'25. Project page: https://dp-recon.github.io/
期刊&会议
CVPR
Conference on Computer Vision and Pattern Recognition · 会议 · Computer Vision
Effortless Active Labeling for Long-Term Test-Time Adaptation
Comments CVPR 2025.Code:https://github.com/flash1803/EATTA
Toward Generalized Image Quality Assessment: Relaxing the Perfect Reference Quality Assumption
Comments Accepted by CVPR 2025
Mitigating Ambiguities in 3D Classification with Gaussian Splatting
Comments Accepted by CVPR 2025
KeyFace: Expressive Audio-Driven Facial Animation for Long Sequences via KeyFrame Interpolation
Comments CVPR 2025
The PanAf-FGBG Dataset: Understanding the Impact of Backgrounds in Wildlife Behaviour Recognition
Comments 2025 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)
Towards Long-Horizon Vision-Language Navigation: Platform, Benchmark and Method
Comments Accepted by CVPR 2025. A novel Long-Horizon Vision-Language Navigation task, project page: https://hcplab-sysu.github.io/LH-VLN/
DepthCues: Evaluating Monocular Depth Perception in Large Vision Models
Comments Accepted to CVPR 2025. Project page: https://danier97.github.io/depthcues/
DORNet: A Degradation Oriented and Regularized Network for Blind Depth Super-Resolution
Comments CVPR 2025
Distilling Long-tailed Datasets
Comments CVPR 2025. Code is available at https://github.com/ichbill/LTDD
Global Transport for Fluid Reconstruction with Learned Self-Supervision
Comments CVPR 2021 oral, source code: https://github.com/tum-pbs/Global-Flow-Transport
Multi-view Reconstruction via SfM-guided Monocular Depth Estimation
Comments CVPR 2025. Project page: https://zju3dv.github.io/murre/
Bridging Past and Future: End-to-End Autonomous Driving with Historical Prediction and Planning
Comments CVPR 2025
SketchFusion: Learning Universal Sketch Features through Fusing Foundation Models
Comments Accepted in CVPR 2025. Project page available at https://subhadeepkoley.github.io/SketchFusion/
Rethinking End-to-End 2D to 3D Scene Segmentation in Gaussian Splatting
Comments CVPR 2025. The code is publicly available at this https URL (https://github.com/Runsong123/Unified-Lift)
MP-GUI: Modality Perception with MLLMs for GUI Understanding
Comments Paper accepted to CVPR 2025
DIFFVSGG: Diffusion-Driven Online Video Scene Graph Generation
Comments CVPR 2025, Code: https://github.com/kagawa588/DiffVsgg
SALAD: Skeleton-aware Latent Diffusion for Text-driven Motion Generation and Editing
Comments CVPR 2025; Project page https://seokhyeonhong.github.io/projects/salad/
Learning from Synchronization: Self-Supervised Uncalibrated Multi-View Person Association in Challenging Scenes
Comments Accepted for CVPR 2025. Code: https://github.com/CAMMA-public/Self-MVA
Omnia de EgoTempo: Benchmarking Temporal Understanding of Multi-Modal LLMs in Egocentric Videos
Comments Accepted to CVPR 2025. Dataset and code are available at https://github.com/google-research-datasets/egotempo.git
MOS: Modeling Object-Scene Associations in Generalized Category Discovery
Comments Accepted to CVPR 2025.The code is available at https://github.com/JethroPeng/MOS
UniGoal: Towards Universal Zero-shot Goal-oriented Navigation
Comments Accepted to CVPR 2025. Project page: https://bagh2178.github.io/UniGoal/
Towards Practical Real-Time Neural Video Compression
Comments CVPR 2025. Visit the project page at https://dcvccodec.github.io and access the code at https://github.com/microsoft/DCVC
Balanced Rate-Distortion Optimization in Learned Image Compression
Comments Accepted to CVPR 2025
Order-Robust Class Incremental Learning: Graph-Driven Dynamic Similarity Grouping
Comments Accepted to CVPR 2025
MoVE-KD: Knowledge Distillation for VLMs with Mixture of Visual Encoders
Comments Accepted by CVPR 2025
Temporally Consistent Object-Centric Learning by Contrasting Slots
Comments Published at CVPR 2025
VISCO: Benchmarking Fine-Grained Critique and Correction Towards Self-Improvement in Visual Reasoning
Comments CVPR 2025. https://visco-benchmark.github.io/
Timestep Embedding Tells: It's Time to Cache for Video Diffusion Model
Comments Accepted in CVPR 2025. Project: https://liewfeng.github.io/TeaCache
DAGSM: Disentangled Avatar Generation with GS-enhanced Mesh
Comments Accepted by CVPR 2025
