大学 × Computer Vision
大阪大学
Computer Vision / 2021–2025 確定版
掲載論文 43 本
論文一覧
43 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 43 本と一致しています。
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
2021年
- Graph Stacked Hourglass Networks for 3D Human Pose Estimation
掲載ID:
doi:10.1109/cvpr46437.2021.01584 - Lighting, Reflectance and Geometry Estimation From 360deg Panoramic Stereo
掲載ID:
cvf:cvpr2021:c3a6d315bede60376ebb36b5 - Multispectral Photometric Stereo for Spatially-Varying Spectral Reflectances: A Well Posed Problem?
掲載ID:
doi:10.1109/cvpr46437.2021.00102 - Normal Integration via Inverse Plane Fitting With Minimum Point-to-Plane Distance
掲載ID:
doi:10.1109/cvpr46437.2021.00241 - A Closer Look at Rotation-Invariant Deep Point Cloud Analysis
掲載ID:
doi:10.1109/iccv48922.2021.01591 - Explain Me the Painting: Multi-Topic Knowledgeable Art Description Generation
掲載ID:
doi:10.1109/iccv48922.2021.00537 - Generalized Shuffled Linear Regression
掲載ID:
doi:10.1109/iccv48922.2021.00641 - SCOUTER: Slot Attention-Based Classifier for Explainable Image Recognition
掲載ID:
doi:10.1109/iccv48922.2021.00108
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。