Reconfusion: 3d reconstruction with diffusion priors

R Wu, B Mildenhall, P Henzler, K Park… - Proceedings of the …, 2024 - openaccess.thecvf.com
Abstract 3D reconstruction methods such as Neural Radiance Fields (NeRFs) excel at
rendering photorealistic novel views of complex scenes. However recovering a high-quality …

Dngaussian: Optimizing sparse-view 3d gaussian radiance fields with global-local depth normalization

J Li, J Zhang, X Bai, J Zheng, X Ning… - Proceedings of the …, 2024 - openaccess.thecvf.com
Radiance fields have demonstrated impressive performance in synthesizing novel views
from sparse input views yet prevailing methods suffer from high training costs and slow …

Semantically-aware Neural Radiance Fields for Visual Scene Understanding: A Comprehensive Review

TAQ Nguyen, A Bourki, M Macudzinski… - arXiv preprint arXiv …, 2024 - arxiv.org
This review thoroughly examines the role of semantically-aware Neural Radiance Fields
(NeRFs) in visual scene understanding, covering an analysis of over 250 scholarly papers. It …

Reducing shape-radiance ambiguity in radiance fields with a closed-form color estimation method

Q Fang, Y Song, K Li, L Bo - Advances in Neural …, 2024 - proceedings.neurips.cc
Neural radiance field (NeRF) enables the synthesis of cutting-edge realistic novel view
images of a 3D scene. It includes density and color fields to model the shape and radiance …

Nerf revisited: Fixing quadrature instability in volume rendering

MA Uy, K Nakayama, G Yang… - Advances in …, 2024 - proceedings.neurips.cc
Neural radiance fields (NeRF) rely on volume rendering to synthesize novel views. Volume
rendering requires evaluating an integral along each ray, which is numerically approximated …

Därf: Boosting radiance fields from sparse input views with monocular depth adaptation

J Song, S Park, H An, S Cho… - Advances in Neural …, 2023 - proceedings.neurips.cc
Neural radiance field (NeRF) shows powerful performance in novel view synthesis and 3D
geometry reconstruction, but it suffers from critical performance degradation when the …

Global and Hierarchical Geometry Consistency Priors for Few-shot NeRFs in Indoor Scenes

X Sun, Q Xu, X Yang, Y Zang… - Proceedings of the IEEE …, 2024 - openaccess.thecvf.com
It is challenging for Neural Radiance Fields (NeRFs) in the few-shot setting to reconstruct
high-quality novel views and depth maps in 360^\circ outward-facing indoor scenes. The …

G3DR: Generative 3D Reconstruction in ImageNet

P Reddy, I Elezi, J Deng - … of the IEEE/CVF Conference on …, 2024 - openaccess.thecvf.com
We introduce a novel 3D generative method Generative 3D Reconstruction (G3DR) in
ImageNet capable of generating diverse and high-quality 3D objects from single images …

High-Resolution and Few-Shot View Synthesis from Asymmetric Dual-Lens Inputs

R Xu, M Yao, Y Li, Y Zhang, Z Xiong - European Conference on Computer …, 2025 - Springer
Novel view synthesis has achieved remarkable quality and efficiency by the paradigm of 3D
Gaussian Splatting (3D-GS), but still faces two challenges: 1) significant performance …

BoostMVSNeRFs: Boosting MVS-based NeRFs to Generalizable View Synthesis in Large-scale Scenes

CH Su, CY Hu, SR Tsai, JY Lee, CY Lin… - ACM SIGGRAPH 2024 …, 2024 - dl.acm.org
While Neural Radiance Fields (NeRFs) have demonstrated exceptional quality, their
protracted training duration remains a limitation. Generalizable and MVS-based NeRFs …