CVMeta22
* *Computer Vision for Metaverse
* Avatargen: A 3d Generative Model for Animatable Human Avatars
* Implicit Map Augmentation for Relocalization
* INGeo: Accelerating Instant Neural Scene Reconstruction with Noisy Geometry Priors
* Initialization and Alignment for Adversarial Texture Optimization
* LWA-Hand: Lightweight Attention Hand for Interacting Hand Reconstruction
* Neural Mesh-based Graphics
* Number-Adaptive Prototype Learning for 3D Point Cloud Semantic Segmentation
* One-shot Learning for Human Affordance Detection
* Photo-realistic 360° Head Avatars in the Wild
* Racial Bias in the Beautyverse: Evaluation of Augmented-Reality Beauty Filters
* Self-supervised 3d Human Pose Estimation in Static Video via Neural Rendering
* Signet: Intrinsic Image Decomposition by a Semantic and Invariant Gradient Driven Network for Indoor Scenes
* Social Processes: Self-supervised Meta-learning Over Conversational Groups for Forecasting Nonverbal Social Cues
14 for CVMeta22
CVMeta23
* *Computer Vision for Metaverse
* BoDiffusion: Diffusing Sparse Observations for Full-Body Human Motion Synthesis
* Effective Whole-body Pose Estimation with Two-stages Distillation
* Efficient 3D Reconstruction, Streaming and Visualization of Static and Dynamic Scene Parts for Multi-client Live-telepresence in Large-scale Environments
* Extract-and-Adaptation Network for 3D Interacting Hand Mesh Recovery
* FArMARe: a Furniture-Aware Multi-task methodology for Recommending Apartments based on the user interests
* Generative Approach for Probabilistic Human Mesh Recovery using Diffusion Models
* Intrinsic Appearance Decomposition Using Point Cloud Representation
* MAMMOS: MApping Multiple human MOtion with Scene understanding and natural interactions
* Noise-in, Bias-out: Balanced and Real-time MoCap Solving
* NOVA: NOvel View Augmentation for Neural Composition of Dynamic Objects
* On-device Real-time Custom Hand Gesture Recognition
* Personalized 3D Human Pose and Shape Refinement
* Temporally Consistent Semantic Segmentation using Spatially Aware Multi-view Semantic Fusion for Indoor RGB-D videos
* UPGPT: Universal Diffusion Model for Person Image Generation, Editing and Pose Transfer
15 for CVMeta23
CVMeta25
* ARC-NeRF: Area Ray Casting for Broader Unseen View Coverage in Few-Shot Object Rendering
* DeclutterNeRF: Generative-Free 3D Scene Recovery for Occlusion Removal
* Direction-Aware Hybrid Representation Learning for 3D Hand Pose and Shape Estimation
* ePBR: Extended PBR Materials in Image Synthesis
* FaceGest: A Comprehensive Facial Gesture Dataset for Human-Computer Interaction
* FreBIS: Frequency-Based Stratification for Neural Implicit Surface Representations
* HumMorph: Generalized Dynamic Human Neural Fields From Few Views
* IL-NeRF: Incremental Learning for Neural Radiance Fields with Camera Pose Alignment
* OccludeNeRF: Geometry-Aware 3D Scene Inpainting with Collaborative Score Distillation in NeRF
* PanoDreamer: Consistent Text to 360-Degree Scene Generation
* PlückeRF: A Line-Based 3D Representation for Few-View Reconstruction
* SplatMesh: Interactive 3D Segmentation and Editing Using Mesh-Based Gaussian Splatting
* What Makes for a Good Stereoscopic Image?
13 for CVMeta25