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
Diffusion Renderer: Neural Inverse and Forward Rendering with Video Diffusion Models
Diffusion Self-Distillation for Zero-Shot Customized Image Generation
DiffusionSfM: Predicting Structure and Motion via Ray Origin and Endpoint Diffusion
DiffVsgg: Diffusion-Driven Online Video Scene Graph Generation
DifIISR: A Diffusion Model with Gradient Guidance for Infrared Image Super-Resolution
DIFIX3D+: Improving 3D Reconstructions with Single-Step Diffusion Models
Digital Twin Catalog: A Large-Scale Photorealistic 3D Object Digital Twin Dataset
DiGIT: Multi-Dilated Gated Encoder and Central-Adjacent Region Integrated Decoder for Temporal Action Detection Transformer
DiG: Scalable and Efficient Diffusion Models with Gated Linear Attention
DiN: Diffusion Model for Robust Medical VQA with Semantic Noisy Labels
Dinomaly: The Less Is More Philosophy in Multi-Class Unsupervised Anomaly Detection
DINOv2 Meets Text: A Unified Framework for Image- and Pixel-Level Vision-Language Alignment
DIO: Decomposable Implicit 4D Occupancy-Flow World Model
DI-PCG: Diffusion-based Efficient Inverse Procedural Content Generation for High-quality 3D Asset Creation
Directional Label Diffusion Model for Learning from Noisy Labels
DiSciPLE: Learning Interpretable Programs for Scientific Visual Discovery
Disco4D: Disentangled 4D Human Generation and Animation from a Single Image
Discovering Fine-Grained Visual-Concept Relations by Disentangled Optimal Transport Concept Bottleneck Models
Discovering Hidden Visual Concepts Beyond Linguistic Input in Infant Learning
DiscoVLA: Discrepancy Reduction in Vision, Language, and Alignment for Parameter-Efficient Video-Text Retrieval
Discrete to Continuous: Generating Smooth Transition Poses from Sign Language Observations
Disentangled Pose and Appearance Guidance for Multi-Pose Generation
Disentangling Safe and Unsafe Image Corruptions via Anisotropy and Locality
DiskVPS: Vanishing Point Detector via Hough Transform in a Disk Region
Dispider: Enabling Video LLMs with Active Real-Time Interaction via Disentangled Perception, Decision, and Reaction
DiSRT-In-Bed: Diffusion-Based Sim-to-Real Transfer Framework for In-Bed Human Mesh Recovery
Dissecting and Mitigating Diffusion Bias via Mechanistic Interpretability
Distilled Prompt Learning for Incomplete Multimodal Survival Prediction
Distilling Long-tailed Datasets
Distilling Monocular Foundation Model for Fine-grained Depth Completion
Distilling Spatially-Heterogeneous Distortion Perception for Blind Image Quality Assessment
Distilling Spectral Graph for Object-Context Aware Open-Vocabulary Semantic Segmentation
DistinctAD: Distinctive Audio Description Generation in Contexts
Distinguish Then Exploit: Source-free Open Set Domain Adaptation via Weight Barcode Estimation and Sparse Label Assignment
Distraction is All You Need for Multimodal Large Language Model Jailbreaking
Distribution Prototype Diffusion Learning for Open-set Supervised Anomaly Detection
DiTASK: Multi-Task Fine-Tuning with Diffeomorphic Transformations
DiTCtrl: Exploring Attention Control in Multi-Modal Diffusion Transformer for Tuning-Free Multi-Prompt Longer Video Generation
DIV-FF: Dynamic Image-Video Feature Fields For Environment Understanding in Egocentric Videos
Divide and Conquer: Heterogeneous Noise Integration for Diffusion-based Adversarial Purification
Divot: Diffusion Powers Video Tokenizer for Comprehension and Generation
DivPrune: Diversity-based Visual Token Pruning for Large Multimodal Models
DKC: Differentiated Knowledge Consolidation for Cloth-Hybrid Lifelong Person Re-identification
DKDM: Data-Free Knowledge Distillation for Diffusion Models with Any Architecture
DL2G: Degradation-guided Local-to-Global Restoration for Eyeglass Reflection Removal
DNF: Unconditional 4D Generation with Dictionary-based Neural Fields
DnLUT: Ultra-Efficient Color Image Denoising via Channel-Aware Lookup Tables
DocLayLLM: An Efficient Multi-modal Extension of Large Language Models for Text-rich Document Understanding
Do Computer Vision Foundation Models Learn the Low-level Characteristics of the Human Visual System?
Docopilot: Improving Multimodal Models for Document-Level Understanding

« prev Page 13/59 next »