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
EdgeDiff: Edge-aware Diffusion Network for Building Reconstruction from Point Clouds
EdgeMovingNet: Edge-preserving Point Cloud Reconstruction via Joint Geometry Features
Edge-SD-SR: Low Latency and Parameter Efficient On-device Super-Resolution with Stable Diffusion via Bidirectional Conditioning
EdgeTAM: On-Device Track Anything Model
EditAR: Unified Conditional Generation with Autoregressive Models
Edit Away and My Face Will not Stay: Personal Biometric Defense against Malicious Generative Editing
EditSplat: Multi-View Fusion and Attention-Guided Optimization for View-Consistent 3D Scene Editing with 3D Gaussian Splatting
EDM: Equirectangular Projection-Oriented Dense Kernelized Feature Matching
Effective Cloud Removal for Remote Sensing Images by an Improved Mean-Reverting Denoising Model with Elucidated Design Space
Effective SAM Combination for Open-Vocabulary Semantic Segmentation
Efficient ANN-Guided Distillation: Aligning Rate-based Features of Spiking Neural Networks through Hybrid Block-wise Replacement
Efficient Data Driven Mixture-of-Expert Extraction from Trained Networks
Efficient Decoupled Feature 3D Gaussian Splatting via Hierarchical Compression
Efficient Depth Estimation for Unstable Stereo Camera Systems on AR Glasses
Efficient Diffusion as Low Light Enhancer
Efficient Dynamic Scene Editing via 4D Gaussian-based Static-Dynamic Separation
Efficient Event-Based Object Detection: A Hybrid Neural Network with Spatial and Temporal Attention
Efficient Fine-Tuning and Concept Suppression for Pruned Diffusion Models
EfficientLLaVA: Generalizable Auto-Pruning for Large Vision-language Models
Efficient Long Video Tokenization via Coordinate-based Patch Reconstruction
Efficiently Reconstructing Dynamic Scenes One D4RT at a Time
Efficient Motion-Aware Video MLLM
Efficient Personalization of Quantized Diffusion Model without Backpropagation
Efficient Test-time Adaptive Object Detection via Sensitivity-Guided Pruning
Efficient Transfer Learning for Video-language Foundation Models
Efficient Video Face Enhancement with Enhanced Spatial-Temporal Consistency
Efficient Video Super-Resolution for Real-time Rendering with Decoupled G-buffer Guidance
EfficientViM: Efficient Vision Mamba with Hidden State Mixer based State Space Duality
Efficient Visual State Space Model for Image Deblurring
EffiDec3D: An Optimized Decoder for High-Performance and Efficient 3D Medical Image Segmentation
Effortless Active Labeling for Long-Term Test-Time Adaptation
Ego4o: Egocentric Human Motion Capture and Understanding from Multi-Modal Input
EgoEdit: Dataset, Real-Time Streaming Model, and Benchmark for Egocentric Video Editing
EgoLife: Towards Egocentric Life Assistant
EgoLM: Multi-Modal Language Model of Egocentric Motions
EgoPressure: A Dataset for Hand Pressure and Pose Estimation in Egocentric Vision
EgoTextVQA: Towards Egocentric Scene-Text Aware Video Question Answering
EIDT-V: Exploiting Intersections in Diffusion Trajectories for Model-Agnostic, Zero-Shot, Training-Free Text-to-Video Generation
EigenGS Representation: From Eigenspace to Gaussian Image Space
Electromyography-Informed Facial Expression Reconstruction for Physiological-Based Synthesis and Analysis
Embodied Scene Understanding for Vision Language Models via MetaVQA
Embracing Collaboration Over Competition: Condensing Multiple Prompts for Visual In-Context Learning
EmoDubber: Towards High Quality and Emotion Controllable Movie Dubbing
EmoEdit: Evoking Emotions through Image Manipulation
EMOE: Modality-Specific Enhanced Dynamic Emotion Experts
EmotiveTalk: Expressive Talking Head Generation through Audio Information Decoupling and Emotional Video Diffusion
EMOVA: Empowering Language Models to See, Hear and Speak with Vivid Emotions
Emphasizing Discriminative Features for Dataset Distillation in Complex Scenarios
Empowering Large Language Models with 3D Situation Awareness
Empowering LLMs to Understand and Generate Complex Vector Graphics

« prev Page 16/59 next »