CVPR 2025

2,907 papers

Top Research Directions

Research directions most represented by CVPR 2025 papers.

Overcoming the Static Scene Assumption 49
Mitigating Multi View Inconsistency in Generative 3D Modeling 48
Eliminating Per-Scene Optimization with Feed-Forward 3D Reconstruction 42
Generalizing from Synthetic Data to the Real World 39
Material Lighting Disentanglement for 3D Reconstruction 37
Spatial Attention Masking in Generative Diffusion Models 36
Error Propagation in Monocular Depth Priors 32
Overcoming the Iterative Inference Latency of Diffusion Models 31
Exploiting Temporal Redundancy in Video Neural Networks 29
Aligning Global Semantics with Local Spatial Precision 28
Scaling Visual Attention Beyond Quadratic Complexity 28
Accelerating Neural Scene Representations for Real Time Rendering 27
Visual Grounding and Hallucination in Vision Language Models 27
Completing Unobserved Geometry with Generative Diffusion Priors 24
The Cross Modal Representation Gap 24

Top Authors

AuthorPapers
Yujun Shen17
Marc Pollefeys15
Daniel Cremers13
Jian Yang13
Jan Kautz11
Ziwei Liu11
Federico Tombari10
Guangtao Zhai10
Jiangning Zhang10
Christian Theobalt9
Jiajun Wu9
Ming-Hsuan Yang9
Ranjay Krishna9
Wei-Shi Zheng9
Xiongkuo Min9
Zhe Lin9
Zheng-Jun Zha9
Andrea Vedaldi8
Chen Change Loy8
Cheng Wang8

Impactful Papers

Papers from CVPR 2025 that shaped research clusters.

Foundational

Influential

Papers

Title
Stealthy Backdoor Attack in Self-Supervised Learning Vision Encoders for Large Vision Language Models
Steepest Descent Density Control for Compact 3D Gaussian Splatting
Steering Away from Harm: An Adaptive Approach to Defending Vision Language Model Against Jailbreaks
STEP: Enhancing Video-LLMs' Compositional Reasoning by Spatio-Temporal Graph-guided Self-Training
STEPS: Sequential Probability Tensor Estimation for Text-to-Image Hard Prompt Search
Stereo4D: Learning How Things Move in 3D from Internet Stereo Videos
Stereo Anywhere: Robust Zero-Shot Deep Stereo Matching Even Where Either Stereo or Mono Fail
STEREO: A Two-Stage Framework for Adversarially Robust Concept Erasing from Text-to-Image Diffusion Models
StickMotion: Generating 3D Human Motions by Drawing a Stickman
STiL: Semi-supervised Tabular-Image Learning for Comprehensive Task-Relevant Information Exploration in Multimodal Classification
STING-BEE: Towards Vision-Language Model for Real-World X-ray Baggage Security Inspection
STINR: Deciphering Spatial Transcriptomics via Implicit Neural Representation
Stochastic Human Motion Prediction with Memory of Action Transition and Action Characteristic
STOP: Integrated Spatial-Temporal Dynamic Prompting for Video Understanding
Stop Learning it all to Mitigate Visual Hallucination, Focus on the Hallucination Target
Stop Walking in Circles! Bailing Out Early in Projected Gradient Descent
STPro: Spatial and Temporal Progressive Learning for Weakly Supervised Spatio-Temporal Grounding
StreetCrafter: Street View Synthesis with Controllable Video Diffusion Models
Stretching Each Dollar: Diffusion Training from Scratch on a Micro-Budget
Structure-Aware Correspondence Learning for Relative Pose Estimation
Structured 3D Latents for Scalable and Versatile 3D Generation
Structure from Collision
Structure-from-Motion with a Non-Parametric Camera Model
Style-Editor: Text-driven Object-centric Style Editing
Style Evolving along Chain-of-Thought for Unknown-Domain Object Detection
StyleMaster: Stylize Your Video with Artistic Generation and Translation
Style Quantization for Data-Efficient GAN Training
StyleSSP: Sampling StartPoint Enhancement for Training-free Diffusion-based Method for Style Transfer
StyleStudio: Text-Driven Style Transfer with Selective Control of Style Elements
Subnet-Aware Dynamic Supernet Training for Neural Architecture Search
Subspace Constraint and Contribution Estimation for Heterogeneous Federated Learning
Sufficient Invariant Learning for Distribution Shift
SUM Parts: Benchmarking Part-Level Semantic Segmentation of Urban Meshes
SuperLightNet: Lightweight Parameter Aggregation Network for Multimodal Brain Tumor Segmentation
SuperPC: A Single Diffusion Model for Point Cloud Completion, Upsampling, Denoising, and Colorization
Supervising Sound Localization by In-the-wild Egomotion
SURGEON: Memory-Adaptive Fully Test-Time Adaptation via Dynamic Activation Sparsity
SVDC: Consistent Direct Time-of-Flight Video Depth Completion with Frequency Selective Fusion
SVFR: A Unified Framework for Generalized Video Face Restoration
SVG-IR: Spatially-Varying Gaussian Splatting for Inverse Rendering
SVLTA: Benchmarking Vision-Language Temporal Alignment via Synthetic Video Situation
SwiftEdit: Lightning Fast Text-Guided Image Editing via One-Step Diffusion
Symbolic Representation for Any-to-Any Generative Tasks
SymDPO: Boosting In-Context Learning of Large Multimodal Models with Symbol Demonstration Direct Preference Optimization
Symmetry Strikes Back: From Single-Image Symmetry Detection to 3D Generation
Synchronized Video-to-Audio Generation via Mel Quantization-Continuum Decomposition
SyncSDE: A Probabilistic Framework for Diffusion Synchronization
SyncVP: Joint Diffusion for Synchronous Multi-Modal Video Prediction
SynerGen-VL: Towards Synergistic Image Understanding and Generation with Vision Experts and Token Folding
SynTab-LLaVA: Enhancing Multimodal Table Understanding with Decoupled Synthesis

« prev Page 50/59 next »