Traversing Distortion-Perception Tradeoff using a Single Score-Based Generative Model
Comments Accepted by IEEE/CVF Conference on Computer Vision and Pattern Recognition 2025
期刊&会议
CVPR
Conference on Computer Vision and Pattern Recognition · 会议 · Computer Vision
TokenHSI: Unified Synthesis of Physical Human-Scene Interactions through Task Tokenization
Comments CVPR 2025
ChatGarment: Garment Estimation, Generation and Editing via Large Language Models
Comments CVPR 2025
ViCaS: A Dataset for Combining Holistic and Pixel-level Video Understanding using Captions with Grounded Segmentation
Comments Accepted to CVPR 2025. Project page: https://ali2500.github.io/vicas-project/
ArtFormer: Controllable Generation of Diverse 3D Articulated Objects
Comments CVPR 2025. impl. repo: https://github.com/ShuYuMo2003/ArtFormer
TAMT: Temporal-Aware Model Tuning for Cross-Domain Few-Shot Action Recognition
Comments Accepted by CVPR 2025; Project page: https://github.com/TJU-YDragonW/TAMT
THRONE: An Object-based Hallucination Benchmark for the Free-form Generations of Large Vision-Language Models
Comments In CVPR 2024. Code https://github.com/amazon-science/THRONE
SocialGesture: Delving into Multi-person Gesture Understanding
Comments CVPR 2025
ESC: Erasing Space Concept for Knowledge Deletion
Comments 22 pages, 14 figures, 18 tables, CVPR 2025
MDP: Multidimensional Vision Model Pruning with Latency Constraint
Comments Accepted at CVPR 2025
Random Conditioning with Distillation for Data-Efficient Diffusion Model Compression
Comments Accepted to CVPR 2025. 8 pages main paper + 4 pages references + 5 pages supplementary, 9 figures in total
OccludeNeRF: Geometric-aware 3D Scene Inpainting with Collaborative Score Distillation in NeRF
Comments CVPR 2025 CV4Metaverse
Geometry in Style: 3D Stylization via Surface Normal Deformation
Comments CVPR 2025. Our project page is at https://threedle.github.io/geometry-in-style
Parallelized Autoregressive Visual Generation
Comments CVPR 2025 Accepted - Project Page: https://yuqingwang1029.github.io/PAR-project
CARL: A Framework for Equivariant Image Registration
Comments CVPR 2025
Detecting Out-of-Distribution Through the Lens of Neural Collapse
Comments CVPR 2025 main conference paper
Implicit Bias Injection Attacks against Text-to-Image Diffusion Models
Comments Accept to CVPR 2025
BlenderGym: Benchmarking Foundational Model Systems for Graphics Editing
Comments CVPR 2025 Accepted
A$^\text{T}$A: Adaptive Transformation Agent for Text-Guided Subject-Position Variable Background Inpainting
Comments Accepted by CVPR 2025
v-CLR: View-Consistent Learning for Open-World Instance Segmentation
Comments Accepted by CVPR 2025, Project page: https://visual-ai.github.io/vclr, Code: https://github.com/Visual-AI/vCLR
Prompt-Guided Attention Head Selection for Focus-Oriented Image Retrieval
Comments Accepted to CVPR 2025 PixFoundation Workshop
Lux Post Facto: Learning Portrait Performance Relighting with Conditional Video Diffusion and a Hybrid Dataset
Comments CVPR 2025
DivPrune: Diversity-based Visual Token Pruning for Large Multimodal Models
Comments Accepted to CVPR 2025
Denoising Functional Maps: Diffusion Models for Shape Correspondence
Comments CVPR 2025; Project page: https://alekseizhuravlev.github.io/denoising-functional-maps/
Transfer Your Perspective: Controllable 3D Generation from Any Viewpoint in a Driving Scene
Comments Accepted to CVPR 2025
Olympus: A Universal Task Router for Computer Vision Tasks
Comments Accepted to CVPR 2025, Project webpage: http://yuanze-lin.me/Olympus_page/
Augmenting Multimodal LLMs with Self-Reflective Tokens for Knowledge-based Visual Question Answering
Comments CVPR 2025
STEREO: A Two-Stage Framework for Adversarially Robust Concept Erasing from Text-to-Image Diffusion Models
Comments Accepted to CVPR-2025. Code: https://github.com/koushiksrivats/robust-concept-erasing
CoMM: A Coherent Interleaved Image-Text Dataset for Multimodal Understanding and Generation
Comments 22 pages, Accepted by CVPR 2025
Dinomaly: The Less Is More Philosophy in Multi-Class Unsupervised Anomaly Detection
Comments IEEE/CVF CVPR 2025
