paper-with-me

홈 › Papers

HyPlaneHead: Rethinking Tri-plane-like Representations in Full-Head Image Synthesis

2025-09-20 · Heyuan Li, Kenkun Liu, Lingteng Qiu, Qi Zuo, Keru Zheng, Zilong Dong, Xiaoguang Han arxiv

Tri-plane-like representations have been widely adopted in 3D-aware GANs for head image synthesis and other 3D object/scene modeling tasks due to their efficiency. However, querying features via Cartesian coordinate projection often leads to feature entanglement, which results in mirroring artifacts. A recent work, SphereHead, attempted to address this issue by introducing spherical tri-planes based on a spherical coordinate system. While it successfully mitigates feature entanglement, SphereHead suffers from uneven mapping between the square feature maps and the spherical planes, leading to inefficient feature map utilization during rendering and difficulties in generating fine image details. Moreover, both tri-plane and spherical tri-plane representations share a subtle yet persistent issue: feature penetration across convolutional channels can cause interference between planes, particularly when one plane dominates the others. These challenges collectively prevent tri-plane-based methods from reaching their full potential. In this paper, we systematically analyze these problems for the first time and propose innovative solutions to address them. Specifically, we introduce a novel hybrid-plane (hy-plane for short) representation that combines the strengths of both planar and spherical planes while avoiding their respective drawbacks. We further enhance the spherical plane by replacing the conventional theta-phi warping with a novel near-equal-area warping strategy, which maximizes the effective utilization of the square feature map. In addition, our generator synthesizes a single-channel unified feature map instead of multiple feature maps in separate channels, thereby effectively eliminating feature penetration. With a series of technical improvements, our hy-plane representation enables our method, HyPlaneHead, to achieve state-of-the-art performance in full-head image synthesis.

📄 PDF Abstract BibTeX arXiv:2509.16748

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

DaRePlane: Direction-aware Representations for Dynamic Scene Reconstruction

2024-10-18 · Ange Lou, Benjamin Planche, Zhongpai Gao, Yamin Li 외

Numerous recent approaches to modeling and re-rendering dynamic scenes leverage plane-based explicit representations, addressing slow training times associated with models like neural radiance fields (NeRF) and Gaussian …

NeRFNovel View Synthesis

PlaneSAM: Multimodal Plane Instance Segmentation Using the Segment Anything Model

2024-10-21 · Zhongchen Deng, Zhechen Yang, Chi Chen, Cheng Zeng 외

Plane instance segmentation from RGB-D data is a crucial research topic for many downstream tasks. However, most existing deep-learning-based methods utilize only information within the RGB bands, neglecting the importan…

Instance SegmentationPlane Instance SegmentationSegmentationSemantic Segmentation

Mutual information estimation for graph convolutional neural networks

2022-03-31 · Marius C. Landverk, Signe Riemer-Sørensen

Measuring model performance is a key issue for deep learning practitioners. However, we often lack the ability to explain why a specific architecture attains superior predictive accuracy for a given data set. Often, vali…

Inductive BiasInformation PlaneMutual Information Estimation

Learning Dense Correspondence for NeRF-Based Face Reenactment

2023-12-16 · Songlin Yang, Wei Wang, Yushi Lan, Xiangyu Fan 외

Face reenactment is challenging due to the need to establish dense correspondence between various face representations for motion transfer. Recent studies have utilized Neural Radiance Field (NeRF) as fundamental represe…

Face ReenactmentNeRF

Rethinking Non-Negative Matrix Factorization with Implicit Neural Representations

2024-04-05 · Krishna Subramani, Paris Smaragdis, Takuya Higuchi, Mehrez Souden

Non-negative Matrix Factorization (NMF) is a powerful technique for analyzing regularly-sampled data, i.e., data that can be stored in a matrix. For audio, this has led to numerous applications using time-frequency (TF) …