94 citations · 561 across the 60 of their papers we have counts for
54 papers · 1 filter
Solv3R: 3D Looped Transformer as a Multi-view Solver
Jeong-gi Kwak, Andrea Tagliasacchi, Sho Kagami +2
Classical structure-from-motion reconstruction proceeds iteratively, refining camera poses and scene geometry from a current estimate. This allows maps to easily expand without rec…
NoKSR: Kernel-Free Neural Surface Reconstruction via Point Cloud Serialization
Zhen Li, Weiwei Sun, Shrisudhan Govindarajan +4
We present a novel approach to large-scale point cloud surface reconstruction by developing an efficient framework that converts an irregular point cloud into a signed distance fie…
Radiant Foam: Real-Time Differentiable Ray Tracing
Shrisudhan Govindarajan, Daniel Rebain, Kwang Moo Yi +1
Research on differentiable scene representations is consistently moving towards more efficient, real-time models. Recently, this has led to the popularization of splatting methods,…
Lagrangian Hashing for Compressed Neural Field Representations
Shrisudhan Govindarajan, Zeno Sambugaro, Akhmedkhan +7
We present Lagrangian Hashing, a representation for neural fields combining the characteristics of fast training NeRF methods that rely on Eulerian grids (i.e.~InstantNGP), with th…
Evaluating Alternatives to SFM Point Cloud Initialization for Gaussian Splatting
Yalda Foroutan, Daniel Rebain, Kwang Moo Yi +1
3D Gaussian Splatting has recently been embraced as a versatile and effective method for scene reconstruction and novel view synthesis, owing to its high-quality results and compat…
BANF: Band-limited Neural Fields for Levels of Detail Reconstruction
Ahan Shabanov, Shrisudhan Govindarajan, Cody Reading +4
Largely due to their implicit nature, neural fields lack a direct mechanism for filtering, as Fourier analysis from discrete signal processing is not directly applicable to these r…
3D Gaussian Splatting as Markov Chain Monte Carlo
Shakiba Kheradmand, Daniel Rebain, Gopal Sharma +6
While 3D Gaussian Splatting has recently become popular for neural rendering, current methods rely on carefully engineered cloning and splitting strategies for placing Gaussians, w…
Weakly Supervised Point Cloud Segmentation via Conservative Propagation of Scene-level Labels
Shaobo Xia, Jun Yue, Kacper Kania +4
We propose a weakly supervised semantic segmentation method for point clouds that predicts "per-point" labels from just "whole-scene" annotations. The key challenge here is the dis…
PointNeRF++: A multi-scale, point-based Neural Radiance Field
Weiwei Sun, Eduard Trulls, Yang-Che Tseng +4
Point clouds offer an attractive source of information to complement images in neural scene representations, especially when few images are available. Neural rendering methods base…
Unsupervised Keypoints from Pretrained Diffusion Models
Eric Hedlin, Gopal Sharma, Shweta Mahajan +5
Unsupervised learning of keypoints and landmarks has seen significant progress with the help of modern neural network architectures, but performance is yet to match the supervised…
Accelerating Neural Field Training via Soft Mining
Shakiba Kheradmand, Daniel Rebain, Gopal Sharma +4
We present an approach to accelerate Neural Field training by efficiently selecting sampling locations. While Neural Fields have recently become popular, it is often trained by uni…
BlendFields: Few-Shot Example-Driven Facial Modeling
Kacper Kania, Stephan J. Garbin, Andrea Tagliasacchi +5
Generating faithful visualizations of human faces requires capturing both coarse and fine-level details of the face geometry and appearance. Existing methods are either data-driven…
Unsupervised Semantic Correspondence Using Stable Diffusion
Eric Hedlin, Gopal Sharma, Shweta Mahajan +4
Text-to-image diffusion models are now capable of generating images that are often indistinguishable from real images. To generate such images, these models must understand the sem…
CC3D: Layout-Conditioned Generation of Compositional 3D Scenes
Sherwin Bahmani, Jeong Joon Park, Despoina Paschalidou +4
In this work, we introduce CC3D, a conditional generative model that synthesizes complex 3D scenes conditioned on 2D semantic scene layouts, trained using single-view images. Diffe…
RobustNeRF: Ignoring Distractors with Robust Losses
Sara Sabour, Suhani Vora, Daniel Duckworth +3
Neural radiance fields (NeRF) excel at synthesizing new views given multi-view, calibrated images of a static scene. When scenes include distractors, which are not persistent durin…
SparsePose: Sparse-View Camera Pose Regression and Refinement
Samarth Sinha, Jason Y. Zhang, Andrea Tagliasacchi +2
Camera pose estimation is a key step in standard 3D reconstruction pipelines that operate on a dense set of images of a single object or scene. However, methods for pose estimation…
nerf2nerf: Pairwise Registration of Neural Radiance Fields
Lily Goli, Daniel Rebain, Sara Sabour +2
We introduce a technique for pairwise registration of neural fields that extends classical optimization-based local registration (i.e. ICP) to operate on Neural Radiance Fields (Ne…
OpenScene: 3D Scene Understanding with Open Vocabularies
Songyou Peng, Kyle Genova, Chiyu "Max" Jiang +3
Traditional 3D scene understanding approaches rely on labeled 3D datasets to train a model for a single task with supervision. We propose OpenScene, an alternative approach where a…
NeuMap: Neural Coordinate Mapping by Auto-Transdecoder for Camera Localization
Shitao Tang, Sicong Tang, Andrea Tagliasacchi +2
This paper presents an end-to-end neural mapping method for camera localization, dubbed NeuMap, encoding a whole scene into a grid of latent codes, with which a Transformer-based a…
Novel View Synthesis with Diffusion Models
Daniel Watson, William Chan, Ricardo Martin-Brualla +3
We present 3DiM, a diffusion model for 3D novel view synthesis, which is able to translate a single input view into consistent and sharp completions across many views. The core com…
Attention Beats Concatenation for Conditioning Neural Fields
Daniel Rebain, Mark J. Matthews, Kwang Moo Yi +3
Neural fields model signals by mapping coordinate inputs to sampled values. They are becoming an increasingly important backbone architecture across many fields from vision and gra…
Volume Rendering Digest (for NeRF)
Andrea Tagliasacchi, Ben Mildenhall
Neural Radiance Fields employ simple volume rendering as a way to overcome the challenges of differentiating through ray-triangle intersections by leveraging a probabilistic notion…
MobileNeRF: Exploiting the Polygon Rasterization Pipeline for Efficient Neural Field Rendering on Mobile Architectures
Zhiqin Chen, Thomas Funkhouser, Peter Hedman +1
Neural Radiance Fields (NeRFs) have demonstrated amazing ability to synthesize images of 3D scenes from novel views. However, they rely upon specialized volumetric rendering algori…
NeuralBF: Neural Bilateral Filtering for Top-down Instance Segmentation on Point Clouds
Weiwei Sun, Daniel Rebain, Renjie Liao +4
We introduce a method for instance proposal generation for 3D point clouds. Existing techniques typically directly regress proposals in a single feed-forward step, leading to inacc…