paper-with-me

홈 › Papers

LentiAvatar: Pseudo-Multiview Reconstruction and Subpixel Prism Rendering for Real-Time Stereoscopic Communication

2026-06-09 · Chufeng Fang, Dongdong Teng, Lilin Liu arxiv

Real-time stereoscopic video communication has long been a goal of immersive telepresence, yet practical systems still require specialized capture rigs or reduce remote users to a single portrait view. We present LentiAvatar, a Gaussian head-avatar system that connects monocular avatar capture with subpixel-encoded glasses-free lenticular display for real-time autostereoscopic communication. From a monocular portrait video, LentiAvatar reconstructs a controllable head avatar and optimizes it for the lateral viewing zones induced by the display. The method uses natural head turns as pseudo-multiview (PMV) supervision to constrain regions that are otherwise weakly observed in monocular training, including hair, ears, jaw contours, and neck boundaries. Reliable side frames are yaw-binned, aligned to virtual cameras, and supervised within a strict head-and-hair domain; contour-aware losses and staged regularization further suppress ghosting, alpha leakage, and depth instability while preserving lateral detail. At runtime, LentiAvatar renders 32 virtual views and encodes them into a 4K lenticular raster with calibrated subpixel-routing masks. The live-tracker prototype sustains 10.65 FPS, and a subject-specific distilled driver raises the same display pipeline to 38.49 FPS.

📄 PDF Abstract BibTeX arXiv:2606.10550

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

Road surface 3d reconstruction based on dense subpixel disparity map estimation

2018-07-05 · Rui Fan, Xiao Ai, Naim Dahnoun

Various 3D reconstruction methods have enabled civil engineers to detect damage on a road surface. To achieve the millimetre accuracy required for road condition assessment, a disparity map with subpixel resolution needs…

3D ReconstructionComputational EfficiencyDisparity EstimationStereo Matching+1

Deceptive-NeRF/3DGS: Diffusion-Generated Pseudo-Observations for High-Quality Sparse-View Reconstruction

2023-05-24 · Xinhang Liu, Jiaben Chen, Shiu-hong Kao, Yu-Wing Tai 외

Novel view synthesis via Neural Radiance Fields (NeRFs) or 3D Gaussian Splatting (3DGS) typically necessitates dense observations with hundreds of input images to circumvent artifacts. We introduce Deceptive-NeRF/3DGS to…

3DGSNeRFNovel View SynthesisSuper-Resolution

Unsupervised Multiview Contrastive Language-Image Joint Learning with Pseudo-Labeled Prompts Via Vision-Language Model for 3D/4D Facial Expression Recognition

2025-05-14 · Muzammil Behzad

In this paper, we introduce MultiviewVLM, a vision-language model designed for unsupervised contrastive multiview representation learning of facial emotions from 3D/4D data. Our architecture integrates pseudo-labels deri…

Contrastive LearningFacial Expression RecognitionLanguage ModelingLanguage Modelling+1

High-Quality Real-Time Rendering Using Subpixel Sampling Reconstruction

2023-01-03 · Boyu Zhang, Hongliang Yuan, Mingyan Zhu, Ligang Liu 외

Generating high-quality, realistic rendering images for real-time applications generally requires tracing a few samples-per-pixel (spp) and using deep learning-based approaches to denoise the resulting low-spp images. Ex…

2kDenoising

MVD$^2$: Efficient Multiview 3D Reconstruction for Multiview Diffusion

2024-02-22 · Xin-Yang Zheng, Hao Pan, Yu-Xiao Guo, Xin Tong 외

As a promising 3D generation technique, multiview diffusion (MVD) has received a lot of attention due to its advantages in terms of generalizability, quality, and efficiency. By finetuning pretrained large image diffusio…

3D Generation3D Reconstruction