activity
20212026
most citedFew-shot Neural Human Performance Rendering from Sparse RGBD Videos

12 citations · 21 across the 10 of their papers we have counts for

collaborators
Showing cs.CVShow all

8 papers · 1 filter

cs.CV2026

CGHair: Compact Gaussian Hair Reconstruction with Card Clustering

Haimin Luo, Srinjay Sarkar, Albert Mosella-Montoro +2

We present a compact pipeline for high-fidelity hair reconstruction from multi-view images. While recent 3D Gaussian Splatting (3DGS) methods achieve realistic results, they often…

cs.CV2023

MVHuman: Tailoring 2D Diffusion with Multi-view Sampling For Realistic 3D Human Generation

Suyi Jiang, Haimin Luo, Haoran Jiang +3

Recent months have witnessed rapid progress in 3D generation based on diffusion models. Most advances require fine-tuning existing 2D Stable Diffsuions into multi-view settings or…

cs.CV2023

Instant-NVR: Instant Neural Volumetric Rendering for Human-object Interactions from Monocular RGBD Stream

Yuheng Jiang, Kaixin Yao, Zhuo Su +3

Convenient 4D modeling of human-object interactions is essential for numerous applications. However, monocular tracking and rendering of complex interaction scenarios remain challe…

cs.CV2022★ 3 cited

NeuralDome: A Neural Modeling Pipeline on Multi-View Human-Object Interactions

Juze Zhang, Haimin Luo, Hongdi Yang +6

Humans constantly interact with objects in daily life tasks. Capturing such processes and subsequently conducting visual inferences from a fixed viewpoint suffers from occlusions,…

cs.CV2022★ 1 cited

HumanGen: Generating Human Radiance Fields with Explicit Priors

Suyi Jiang, Haoran Jiang, Ziyu Wang +3

Recent years have witnessed the tremendous progress of 3D GANs for generating view-consistent radiance fields with photo-realism. Yet, high-quality generation of human radiance fie…

cs.CV2021★ 12 cited

Few-shot Neural Human Performance Rendering from Sparse RGBD Videos

Anqi Pang, Xin Chen, Haimin Luo +3

Recent neural rendering approaches for human activities achieve remarkable view synthesis results, but still rely on dense input views or dense training with all the capture frames…