NEGS-Avatar: Normal Embedded Gaussians for 2D avatar from monocular video

Kanazawa A, Black MJ, Jacobs DW, Malik J. End-to-end recovery of human shape and pose. In: Proceedings of the IEEE conference on computer vision and pattern recognition. 2018, p. 7122–31. 10.1109/cvpr.2018.00744

[3]

Ma Q, Yang J, Tang S, Black MJ. The power of points for modeling humans in clothing. In: Proceedings of the IEEE/CVF international conference on computer vision. 2021, p. 10974–84. 10.1109/iccv48922.2021.01079

[4]

Xiang "Dressing avatars: Deep photorealistic appearance for physically simulated clothing" ACM Trans Graph (2022) 10.1145/3550454.3555456

[5]

Bagautdinov (2021)

[6]

Liao T, Zhang X, Xiu Y, Yi H, Liu X, Qi G-J, Zhang Y, Wang X, Zhu X, Lei Z. High-fidelity clothed avatar reconstruction from a single image. In: Proceedings of the IEEE/CVF conference on computer vision and pattern recognition. 2023, p. 8662–72. 10.1109/cvpr52729.2023.00837

[7]

He T, Xu Y, Saito S, Soatto S, Tung T. Arch++: Animation-ready clothed human reconstruction revisited. In: Proceedings of the IEEE/CVF international conference on computer vision. 2021, p. 11046–56. 10.1109/iccv48922.2021.01086

[8]

"TransPIFu: Combining transformer and pixel-aligned implicit function for single-view clothed human reconstruction" Comput Graph (2023)

[9]

"3DPMesh: An enhanced and novel approach for the reconstruction of 3D human meshes from a single 2D image" Comput Graph (2024)

[10]

NeRF

Ben Mildenhall, Pratul P. Srinivasan, Matthew Tancik et al.

Communications of the ACM 2021 10.1145/3503250

[11]

Peng S, Zhang Y, Xu Y, Wang Q, Shuai Q, Bao H, Zhou X. Neural body: Implicit neural representations with structured latent codes for novel view synthesis of dynamic humans. In: Proceedings of the IEEE/CVF conference on computer vision and pattern recognition. 2021, p. 9054–63. 10.1109/cvpr46437.2021.00894

[12]

Peng S, Zhang S, Xu Z, Geng C, Jiang B, Bao H, Zhou X. Animatable neural implicit surfaces for creating avatars from videos2022;4 (5) arXiv preprint arXiv:2203.08133.

[13]

Instant neural graphics primitives with a multiresolution hash encoding

Thomas Müller, Alex Evans, Christoph Schied et al.

ACM Transactions on Graphics 2022 10.1145/3528223.3530127

[14]

3D Gaussian Splatting for Real-Time Radiance Field Rendering

Bernhard Kerbl, Georgios Kopanas, Thomas Leimkuehler et al.

ACM Transactions on Graphics 2023 10.1145/3592433

[15]

Li Z, Zheng Z, Wang L, Liu Y. Animatable gaussians: Learning pose-dependent gaussian maps for high-fidelity human avatar modeling. In: Proceedings of the IEEE/CVF conference on computer vision and pattern recognition. 2024, p. 19711–22. 10.1109/cvpr52733.2024.01864

[16]

Lei J, Wang Y, Pavlakos G, Liu L, Daniilidis K. Gart: Gaussian articulated template models. In: Proceedings of the IEEE/CVF conference on computer vision and pattern recognition. 2024, p. 19876–87. 10.1109/cvpr52733.2024.01879

[17]

Kocabas M, Chang J-HR, Gabriel J, Tuzel O, Ranjan A. Hugs: Human gaussian splats. In: Proceedings of the IEEE/CVF conference on computer vision and pattern recognition. 2024, p. 505–15. 10.1109/cvpr52733.2024.00055

[18]

Zhan (2024)

[19]

Paudel (2024)

[20]

Hu S, Hong F, Pan L, Mei H, Yang L, Liu Z. Sherf: Generalizable human nerf from a single image. In: Proceedings of the IEEE/CVF international conference on computer vision. 2023, p. 9352–64. 10.1109/iccv51070.2023.00858

[21]

Xu "H-nerf: Neural radiance fields for rendering and temporal reconstruction of humans in motion" Adv Neural Inf Process Syst (2021)

[22]

Jiang "Neuman: Neural human radiance field from a single video" (2022)

[23]

Loper "SMPL: a skinned multi-person linear model" ACM Trans Graph (2015) 10.1145/2816795.2818013

[24]

Wang "Arah: Animatable volume rendering of articulated human sdfs" (2022)

[25]

Masuda (2024)

[26]

Chen "Geometry-guided progressive nerf for generalizable and efficient neural human rendering" (2022)

[27]

Raj A, Zollhofer M, Simon T, Saragih J, Saito S, Hays J, Lombardi S. Pixel-aligned volumetric avatars. In: Proceedings of the IEEE/CVF conference on computer vision and pattern recognition. 2021, p. 11733–42. 10.1109/cvpr46437.2021.01156

[28]

"MT-NeRF: Neural implicit representation based on multi-resolution geometric feature planes" Comput Graph (2025)

[29]

Kwon (2023)

[30]

Peng "Intrinsicngp: Intrinsic coordinate based hash encoding for human nerf" IEEE Trans Vis Comput Graphics (2023)

[31]

Zheng "Avatarrex: Real-time expressive full-body avatars" ACM Trans Graph (2023)

[32]

Fang J, Yi T, Wang X, Xie L, Zhang X, Liu W, Nießner M, Tian Q. Fast dynamic radiance fields with time-aware neural voxels. In: SIGGRAPH Asia 2022 conference papers. 2022, p. 1–9. 10.1145/3550469.3555383

[33]

Hu L, Zhang H, Zhang Y, Zhou B, Liu B, Zhang S, Nie L. Gaussianavatar: Towards realistic human avatar modeling from a single video via animatable 3d gaussians. In: Proceedings of the IEEE/CVF conference on computer vision and pattern recognition. 2024, p. 634–44. 10.1109/cvpr52733.2024.00067

[34]

Jena (2023)

[35]

Zielonka (2023)

[36]

Lin (2024)

[37]

Jiang (2024)

[38]

Zheng S, Zhou B, Shao R, Liu B, Zhang S, Nie L, Liu Y. Gps-gaussian: Generalizable pixel-wise 3d gaussian splatting for real-time human novel view synthesis. In: Proceedings of the IEEE/CVF conference on computer vision and pattern recognition. 2024, p. 19680–90. 10.1109/cvpr52733.2024.01861

[39]

Kwon (2024)

[40]

Hu S, Hu T, Liu Z. Gauhuman: Articulated gaussian splatting from monocular human videos. In: Proceedings of the IEEE/CVF conference on computer vision and pattern recognition. 2024, p. 20418–31. 10.1109/cvpr52733.2024.01930

[41]

Svitov (2024)

[42]

Zhuang Y, Lv J, Wen H, Shuai Q, Zeng A, Zhu H, Chen S, Yang Y, Cao X, Liu W. Idol: Instant photorealistic 3d human creation from a single image. In: Proceedings of the computer vision and pattern recognition conference. 2025, p. 26308–19. 10.1109/cvpr52734.2025.02450

[43]

Qiu (2025)

[44]

Xiu "Icon: Implicit clothed humans obtained from normals" (2022)

[45]

Xiu Y, Yang J, Cao X, Tzionas D, Black MJ. Econ: Explicit clothed humans optimized via normal integration. In: Proceedings of the IEEE/CVF conference on computer vision and pattern recognition. 2023, p. 512–23. 10.1109/cvpr52729.2023.00057

[46]

Wen J, Zhao X, Ren Z, Schwing AG, Wang S. Gomavatar: Efficient animatable human modeling from monocular video using gaussians-on-mesh. In: Proceedings of the IEEE/CVF conference on computer vision and pattern recognition. 2024, p. 2059–69. 10.1109/cvpr52733.2024.00201

[47]

Wang S, Antic B, Geiger A, Tang S. IntrinsicAvatar: Physically Based Inverse Rendering of Dynamic Humans from Monocular Videos via Explicit Ray Tracing. In: Proceedings of the IEEE/CVF conference on computer vision and pattern recognition. 2024, p. 1877–88. 10.1109/cvpr52733.2024.00184

[48]

Goel S, Pavlakos G, Rajasegaran J, Kanazawa A, Malik J. Humans in 4D: Reconstructing and tracking humans with transformers. In: Proceedings of the IEEE/CVF international conference on computer vision. 2023, p. 14783–94. 10.1109/iccv51070.2023.01358

[49]

Jiang Y, Tu J, Liu Y, Gao X, Long X, Wang W, Ma Y. Gaussianshader: 3d gaussian splatting with shading functions for reflective surfaces. In: Proceedings of the IEEE/CVF conference on computer vision and pattern recognition. 2024, p. 5322–32. 10.1109/cvpr52733.2024.00509

[50]

Shi (2023)

Showing 50 of 57 references

Metrics

2

Citations

57

References

Details

Published: Apr 01, 2026
Vol/Issue: 135
Pages: 104538
License: View

Authors

Department of Materials Science and Engineering, College of Engineering, Peking University, Beijing 100871, China

B

Baoquan Zhao

Funding

Shenzhen Science and Technology Innovation Program Award: SYSPG20241211173951079

Cite This Article

Zedan Zheng, Yudi Tan, Zhuo Su, et al. (2026). NEGS-Avatar: Normal Embedded Gaussians for 2D avatar from monocular video. Computers & Graphics, 135, 104538. https://doi.org/10.1016/j.cag.2026.104538

NEGS-Avatar: Normal Embedded Gaussians for 2D avatar from monocular video

You May Also Like