Gaussian grouping: Segment and edit anything in 3d scenes

M Ye, M Danelljan, F Yu, L Ke - European Conference on Computer …, 2025 - Springer
Abstract The recent Gaussian Splatting achieves high-quality and real-time novel-view
synthesis of the 3D scenes. However, it is solely concentrated on the appearance and …

Humangaussian: Text-driven 3d human generation with gaussian splatting

X Liu, X Zhan, J Tang, Y Shan, G Zeng… - Proceedings of the …, 2024 - openaccess.thecvf.com
Realistic 3D human generation from text prompts is a desirable yet challenging task.
Existing methods optimize 3D representations like mesh or neural fields via score distillation …

Sine: Semantic-driven image-based nerf editing with prior-guided editing field

C Bao, Y Zhang, B Yang, T Fan… - Proceedings of the …, 2023 - openaccess.thecvf.com
Despite the great success in 2D editing using user-friendly tools, such as Photoshop,
semantic strokes, or even text prompts, similar capabilities in 3D areas are still limited, either …

Neural feature fusion fields: 3d distillation of self-supervised 2d image representations

V Tschernezki, I Laina, D Larlus… - … Conference on 3D …, 2022 - ieeexplore.ieee.org
We present Neural Feature Fusion Fields (N3F),\a method that improves dense 2D image
feature extractors when the latter are applied to the analysis of multiple images …

vmap: Vectorised object mapping for neural field slam

X Kong, S Liu, M Taher… - Proceedings of the IEEE …, 2023 - openaccess.thecvf.com
We present vMAP, an object-level dense SLAM system using neural field representations.
Each object is represented by a small MLP, enabling efficient, watertight object modelling …

Discoscene: Spatially disentangled generative radiance fields for controllable 3d-aware scene synthesis

Y Xu, M Chai, Z Shi, S Peng… - Proceedings of the …, 2023 - openaccess.thecvf.com
Existing 3D-aware image synthesis approaches mainly focus on generating a single
canonical object and show limited capacity in composing a complex scene containing a …

Removing objects from neural radiance fields

S Weder, G Garcia-Hernando… - Proceedings of the …, 2023 - openaccess.thecvf.com
Abstract Neural Radiance Fields (NeRFs) are emerging as a ubiquitous scene
representation that allows for novel view synthesis. Increasingly, NeRFs will be shareable …

Objectsdf++: Improved object-compositional neural implicit surfaces

Q Wu, K Wang, K Li, J Zheng… - Proceedings of the IEEE …, 2023 - openaccess.thecvf.com
In recent years, neural implicit surface reconstruction has emerged as a popular paradigm
for multi-view 3D reconstruction. Unlike traditional multi-view stereo approaches, the neural …

Semantic-aware implicit neural audio-driven video portrait generation

X Liu, Y Xu, Q Wu, H Zhou, W Wu, B Zhou - European conference on …, 2022 - Springer
Animating high-fidelity video portrait with speech audio is crucial for virtual reality and digital
entertainment. While most previous studies rely on accurate explicit structural information …

Dm-nerf: 3d scene geometry decomposition and manipulation from 2d images

B Wang, L Chen, B Yang - arXiv preprint arXiv:2208.07227, 2022 - arxiv.org
In this paper, we study the problem of 3D scene geometry decomposition and manipulation
from 2D views. By leveraging the recent implicit neural representation techniques …