大学 × Computer Vision
大阪大学
Computer Vision / 2022–2026 LIVE
掲載論文 47 本
論文一覧
47 本
このEditionのランキングに掲載している論文です。同じ大学の複数著者による共著は1本にまとめています。
ランキングの対象論文 47 本と一致しています。
2026年
- BioVITA: Biological Dataset, Model, and Benchmark for Visual-Textual-Acoustic Alignment
掲載ID:
cvf:cvpr2026:66757f63fc9d0b8b30c4856a - Breaking the Scalability Limit of Multi-Projector Calibration with Embedded Cameras
掲載ID:
cvf:cvpr2026:ed413def5e229dd86fa2956d - Cell-Type Prototype-Informed Neural Network for Gene Expression Estimation from Pathology Images
掲載ID:
cvf:cvpr2026:3aa1e2e60ba28e07abe4811b - Coded-E2LF: Coded Aperture Light Field Imaging from Events
掲載ID:
cvf:cvpr2026:71dd1fdcd2bb8f6590198749 - EMMA: Concept Erasure Benchmark with Comprehensive Semantic Metrics and Diverse Categories
掲載ID:
cvf:cvpr2026:9b2f03eb3a6de1a734d7491c - Art Beyond Semantics: Sheaf-Informed Contrastive Learning for Multi-Relational Representations
掲載ID:
ecva:eccv2026:05435 - Don’t Mask Out the Background! Natural-Light Photometric Stereo via Illumination Reconstruction
掲載ID:
ecva:eccv2026:05632 - Driver-WM: A Driver-Centric Traffic-Conditioned Latent World Model for In-Cabin Dynamics Rollout
掲載ID:
ecva:eccv2026:03775 - E3VS-Bench: A Benchmark for Viewpoint-Dependent Active Perception in 3D Gaussian Splatting Scenes
掲載ID:
ecva:eccv2026:04639 - Event-LiDAR: 3D Eventification for Efficient Point Cloud Processing
掲載ID:
ecva:eccv2026:03577 - Gender Bias in Vision-Language In-Context Learning
掲載ID:
ecva:eccv2026:05561 - Invisible Shortcuts: Why Vision Encoders Know Your Camera
掲載ID:
ecva:eccv2026:04431
2025年
- HoGS: Unified Near and Far Object Reconstruction via Homogeneous Gaussian Splatting
掲載ID:
doi:10.1109/cvpr52734.2025.02488 - AgroBench: Vision-Language Model Benchmark in Agriculture
掲載ID:
doi:10.1109/iccv51701.2025.00716 - AnimalClue: Recognizing Animals by their Traces
掲載ID:
doi:10.1109/iccv51701.2025.01371 - Bias in Gender Bias Benchmarks: How Spurious Features Distort Evaluation
掲載ID:
doi:10.1109/iccv51701.2025.00808 - NeuraLeaf: Neural Parametric Leaf Models with Shape and Deformation Disentanglement
掲載ID:
doi:10.1109/iccv51701.2025.02615 - Processing and acquisition traces in visual encoders: What does CLIP know about your camera?
掲載ID:
doi:10.1109/iccv51701.2025.01584 - Spectral Sensitivity Estimation with an Uncalibrated Diffraction Grating
掲載ID:
doi:10.1109/iccv51701.2025.02530 - Taming the Untamed: Graph-Based Knowledge Retrieval and Reasoning for MLLMs to Conquer the Unknown
掲載ID:
doi:10.1109/iccv51701.2025.00450
2024年
- DiLiGenRT: A Photometric Stereo Dataset with Quantified Roughness and Translucency
掲載ID:
doi:10.1109/cvpr52733.2024.01122 - MVCPS-NeuS: Multi-view Constrained Photometric Stereo for Neural Surface Reconstruction
掲載ID:
doi:10.1109/cvpr52733.2024.01935 - NeISF: Neural Incident Stokes Field for Geometry and Material Estimation
掲載ID:
doi:10.1109/cvpr52733.2024.02025 - NeRSP: Neural 3D Reconstruction for Reflective Objects with Sparse Polarized Images
掲載ID:
doi:10.1109/cvpr52733.2024.01123 - Predicated Diffusion: Predicate Logic-Based Attention Guidance for Text-to-Image Diffusion Models
掲載ID:
doi:10.1109/cvpr52733.2024.00826 - Time-Efficient Light-Field Acquisition Using Coded Aperture and Events
掲載ID:
doi:10.1109/cvpr52733.2024.02354 - Would Deep Generative Models Amplify Bias in Future Models?
掲載ID:
doi:10.1109/cvpr52733.2024.01030 - Deep Polarization Cues for Single-shot Shape and Subsurface Scattering Estimation
掲載ID:
doi:10.1007/978-3-031-72855-6_4 - Resolving Scale Ambiguity in Multi-view 3D Reconstruction using Dual-Pixel Sensors
掲載ID:
doi:10.1007/978-3-031-72973-7_10 - Synthesizing Time-varying BRDFs via Latent Space
掲載ID:
doi:10.1007/978-3-031-73209-6_7
2023年
- Deep Curvilinear Editing: Commutative and Nonlinear Image Manipulation for Pretrained Deep Generative Model
掲載ID:
doi:10.1109/cvpr52729.2023.00577 - ECON: Explicit Clothed Humans Optimized via Normal Integration
掲載ID:
doi:10.1109/cvpr52729.2023.00057 - High-Resolution Image Reconstruction With Latent Diffusion Models From Human Brain Activity
掲載ID:
doi:10.1109/cvpr52729.2023.01389 - Inverse Rendering of Translucent Objects Using Physical and Neural Renderers
掲載ID:
doi:10.1109/cvpr52729.2023.01204 - Learning Bottleneck Concepts in Image Classification
掲載ID:
doi:10.1109/cvpr52729.2023.01055 - Model-Agnostic Gender Debiased Image Captioning
掲載ID:
cvf:cvpr2023:ec9711d4a02cda1d53c89059 - Multi-View Azimuth Stereo via Tangent Space Consistency
掲載ID:
doi:10.1109/cvpr52729.2023.00086 - Toward Verifiable and Reproducible Human Evaluation for Text-to-Image Generation
掲載ID:
doi:10.1109/cvpr52729.2023.01372 - Uncurated Image-Text Datasets: Shedding Light on Demographic Bias
掲載ID:
doi:10.1109/cvpr52729.2023.00672 - DiLiGenT-Pi: Photometric Stereo for Planar Surfaces with Rich Details - Benchmark Dataset and Beyond
掲載ID:
cvf:iccv2023:ddcb97aef4ea9aabb6a0a69f - ReLeaPS : Reinforcement Learning-based Illumination Planning for Generalized Photometric Stereo
掲載ID:
doi:10.1109/iccv51070.2023.00841
2022年
- Acquiring a Dynamic Light Field Through a Single-Shot Coded Image
掲載ID:
doi:10.1109/cvpr52688.2022.01921 - AxIoU: An Axiomatically Justified Measure for Video Moment Retrieval
掲載ID:
doi:10.1109/cvpr52688.2022.02040 - Optimal Correction Cost for Object Detection Evaluation
掲載ID:
doi:10.1109/cvpr52688.2022.02043 - Quantifying Societal Bias Amplification in Image Captioning
掲載ID:
doi:10.1109/cvpr52688.2022.01309 - Bilateral Normal Integration
掲載ID:
doi:10.1007/978-3-031-19769-7_32 - Privacy-Preserving Action Recognition via Motion Difference Quantization
掲載ID:
doi:10.1007/978-3-031-19778-9_30
掲載対象外の論文や未反映の論文は、この一覧には含まれません。