WACV-2024-Papers Application 3D Computer Vision Title Repo Paper Video Task-Oriented Human-Object Interactions Generation with Implicit Neural Representations ➖ Depth from Asymmetric Frame-Event Stereo: A Divide-and-Conquer Approach ➖ TriPlaneNet: An Encoder for EG3D Inversion Attentive Prototypes for Source-Free Unsupervised Domain Adaptive 3D Object Detection FIRe: Fast Inverse Rendering using Directional and Signed Distance Functions A Generic and Flexible Regularization Framework for NeRFs ➖ Multi-View 3D Object Reconstruction and Uncertainty Modelling with Neural Shape Prior ➖ Neural Textured Deformable Meshes for Robust Analysis-by-Synthesis ➖ Ray Deformation Networks for Novel View Synthesis of Refractive Objects ➖ Registered and Segmented Deformable Object Reconstruction from a Single View Point Cloud ➖ SupeRVol: Super-Resolution Shape and Reflectance Estimation in Inverse Volume Rendering ➖ RIMeshGNN: A Rotation-Invariant Graph Neural Network for Mesh Classification ➖ OptFlow: Fast Optimization-based Scene Flow Estimation without Supervision ➖ Point-DynRF: Point-based Dynamic Radiance Fields from a Monocular Video ➖ LensNeRF: Rethinking Volume Rendering based on Thin-Lens Camera Model ➖ Domain Adaptive 3D Shape Retrieval from Monocular Images ➖ HD-Fusion: Detailed Text-to-3D Generation Leveraging Multiple Noise Estimation ➖ Sparse Convolutional Networks for Surface Reconstruction from Noisy Point Clouds ➖ Single Frame Semantic Segmentation using Multi-Modal Spherical Images Context-based Interpretable Spatio-Temporal Graph Convolutional Network for Human Motion Forecasting ➖ GC-MVSNet: Multi-View, Multi-Scale, Geometrically-Consistent Multi-View Stereo SAM Fewshot Finetuning for Anatomical Segmentation in Medical Images ➖ MSCC: Multi-Scale Transformers for Camera Calibration ➖ A Geometry Loss Combination for 3D Human Pose Estimation ➖ A Robust Diffusion Modeling Framework for Radar Camera 3D Object Detection ➖ WalkFormer: Point Cloud Completion via Guided Walks ➖ MGM-AE: Self-Supervised Learning on 3D Shape using Mesh Graph Masked Autoencoders ➖ Unsupervised 3D Pose Estimation with Non-Rigid Structure-from-Motion Modeling ➖ Residual Graph Convolutional Network for Bird's-Eye-View Semantic Segmentation ➖ 3D Human Pose Estimation with Two-Step Mixed-Training Strategy ➖ RGB-D Mapping and Tracking in a Plenoxel Radiance Field SOAP: Cross-Sensor Domain Adaptation for 3D Object Detection using Stationary Object Aggregation Pseudo-Labelling ➖ ➖ BALF: Simple and Efficient Blur Aware Local Feature Detector MACP: Efficient Model Adaptation for Cooperative Perception MAELi: Masked Autoencoder for Large-Scale LiDAR Point Clouds ➖ HDMNet: A Hierarchical Matching Network with Double Attention for Large-Scale Outdoor LiDAR Point Cloud Registration ➖ ➖ SGRec3D: Self-Supervised 3D Scene Graph Learning via Object-Level Scene Reconstruction MPT: Mesh Pre-Training with Transformers for Human Pose and Mesh Reconstruction ➖ LInKs ''Lifting Independent Keypoints'' – Partial Pose Lifting for Occlusion Handling with Improved Accuracy in 2D-3D Human Pose Estimation ➖ ➖ ECSIC: Epipolar Cross Attention for Stereo Image Compression Robust Category-Level 3D Pose Estimation from Diffusion-Enhanced Synthetic Data Open-NeRF: Towards Open Vocabulary NeRF Decomposition HAMMER: Learning Entropy Maps to Create Accurate 3D Models in Multi-View Stereo ➖ Polarimetric PatchMatch Multi-View Stereo Solving the Plane-Sphere Ambiguity in Top-Down Structure-from-Motion Self-Annotated 3D Geometric Learning for Smeared Points Removal 3D Face Style Transfer with a Hybrid Solution of NeRF and Mesh Rasterization ➖ A Sequential Learning-based Approach for Monocular Human Performance Capture ➖ ScanEnts3D: Exploiting Phrase-to-3D-Object Correspondences for Improved Visio-Linguistic Models in 3D Scenes ➖ Global Occlusion-Aware Transformer for Robust Stereo Matching MoRF: Mobile Realistic Fullbody Avatars from a Monocular Video ➖ PointCT: Point Central Transformer Network for Weakly-Supervised Point Cloud Semantic Segmentation ➖ Top-Down Beats Bottom-Up in 3D Instance Segmentation Longformer: Longitudinal Transformer for Alzheimer's Disease Classification with Structural MRIs TEGLO: High Fidelity Canonical Texture Mapping from Single-View Images ➖ DiffCLIP: Leveraging Stable Diffusion for Language Grounded 3D Classification FocusTune: Tuning Visual Localization through Focus-Guided Sampling Indoor Visual Localization using Point and Line Correspondences in Dense Colored Point Cloud ➖ Fast Sun-Aligned Outdoor Scene Relighting based on TensoRF ➖ MonoProb: Self-Supervised Monocular Depth Estimation with Interpretable Uncertainty AvatarOne: Monocular 3D Human Animation Deblur-NSFF: Neural Scene Flow Fields for Blurry Dynamic Scenes ➖ SimpliMix: A Simplified Manifold Mixup for Few-Shot Point Cloud Classification PMVC: Promoting Multi-View Consistency for 3D Scene Reconstruction ➖ Hyb-NeRF: A Multiresolution Hybrid Encoding for Neural Radiance Fields ➖ Joint 3D Shape and Motion Estimation from Rolling Shutter Light-Field Images Sharp-NeRF: Grid-based Fast Deblurring Neural Radiance Fields using Sharpness Prior When 3D Bounding-Box Meets SAM: Point Cloud Instance Segmentation with Weak-and-Noisy Supervision ➖ Auto-BPA: An Enhanced Ball-Pivoting Algorithm with Adaptive Radius using Contextual Bandits Towards Realistic Generative 3D Face Models Camera-Independent Single Image Depth Estimation from Defocus Blur U3DS3: Unsupervised 3D Semantic Scene Segmentation ➖ SSP: Semi-Signed Prioritized Neural Fitting for Surface Reconstruction from Unoriented Point Clouds