Nerf
PulseAugur coverage of Nerf — every cluster mentioning Nerf across labs, papers, and developer communities, ranked by signal.
8 day(s) with sentiment data
-
New NeRF-based SLAM system tackles large-scale scene reconstruction
Researchers have developed a new approach to Neural Radiance Fields (NeRF)-based Simultaneous Localization and Mapping (SLAM) designed for large-scale environments. This system utilizes a multi-submap architecture and a…
-
New framework improves 3D model generation from single images
Researchers have developed a new framework for generating 3D models from single images, addressing inconsistencies often found in traditional methods. Their approach uses view-adaptive neural renderers that correct view…
-
DoRF++ uses NeRF and spherical Transformers for advanced Wi-Fi sensing
Researchers have developed DoRF++, a novel approach to Wi-Fi sensing that leverages neural radiance fields (NeRF) to model human motion from Channel State Information (CSI). This method treats Doppler velocity projectio…
-
New UAV3DCrop benchmark evaluates 3D crop reconstruction methods
A new benchmark dataset called UAV3DCrop has been introduced for evaluating 3D reconstruction methods in agricultural settings using unmanned aerial vehicles. The dataset comprises 88,830 images from 91 scenes across va…
-
New SLAM systems UniSim-SLAM and CHOW-SLAM advance accuracy
Two new research papers introduce advanced Simultaneous Localization and Mapping (SLAM) systems that improve accuracy and efficiency. UniSim-SLAM employs a feed-forward approach with a unified optimization framework on …
-
New OASIS framework reconstructs 3D hand avatars from single images
Researchers have developed OASIS, a new framework for reconstructing 3D hand avatars from single images using 3D Gaussian Splatting. This method addresses challenges like self-occlusion and complex deformations by emplo…
-
New benchmarks and models advance AI video generation quality and control · 10 sources tracked
Recent research explores advancements in video generation, focusing on improving physical consistency, controllability, and efficiency. Papers introduce new benchmarks like FilmBench for cinematic quality and UniMoCa fo…
-
Chinese world model UniWorld-View tops Fei-Fei Li's leaderboard
A new world model called UniWorld-View, developed by Tub Zhan Intelligence in collaboration with Peking University and Pengcheng Laboratory, has topped Fei-Fei Li's team's leaderboard. This model can generate novel vide…
-
New Recurrent Sinusoidal INRs Boost High-Fidelity Image and 3D Representation
Researchers have developed a new method using sinusoidal recurrence to enhance implicit neural representations (INRs). This iterative approach enriches the spectral support of latent representations, leading to improved…
-
DINO-SLAM enhances neural representations in SLAM systems
Researchers have developed DINO-SLAM, a novel approach that integrates DINO features into Simultaneous Localization and Mapping (SLAM) systems. This method aims to improve both implicit (NeRF) and explicit (Gaussian Spl…
-
X-Splat uses Gaussian Splatting for 3D dental imaging from single X-rays
Researchers have developed X-Splat, a novel framework utilizing Gaussian splatting to generate 3D cone-beam computed tomography (CBCT) dental volumes from a single panoramic radiograph. This method addresses the underde…
-
New research explores advanced 3D medical image segmentation techniques
Two new research papers explore advanced techniques for 3D medical image segmentation. The first, Consispace, introduces a semantic-aware resampling framework that aims to improve segmentation accuracy by ensuring consi…
-
New methods advance rapid 3D indoor scene reconstruction from panoramic images · 4 sources tracked
Researchers have introduced two new methods for 3D indoor scene reconstruction from panoramic images. Argus, trained on the new Realsee3D dataset, utilizes a learned covisibility module to accurately anchor the metric w…
-
New RLHF method fine-tunes 3D GANs directly from human preferences
Researchers have developed a novel method for fine-tuning 3D-aware generative models, specifically a face GAN called EG3D, using reinforcement learning from human feedback (RLHF). This approach directly optimizes the ne…
-
NeRF-based 3D detector improves autonomous driving perception
Researchers have developed a novel NeRF-Resembled Point-based 3D detector (NeRP3D) that addresses limitations in current NeRF-based pre-training for autonomous driving. Existing methods force NeRFs to work with view tra…
-
New dataset enables novel view synthesis for gastroendoscopy
Researchers have introduced the GastroNVS dataset, the first real-world dataset designed for novel view synthesis (NVS) in gastroendoscopy. This dataset aims to address the current lack of sufficient data for evaluating…
-
Render-FM achieves real-time photorealistic CT scan rendering
Researchers have developed Render-FM, a novel feedforward model designed for real-time photorealistic volumetric rendering of CT scans. This model significantly speeds up the rendering process, reducing it from hours or…
-
VisDom improves sparse novel view synthesis with visible domain constraint · 2 sources tracked
Researchers have introduced VisDom, a novel geometric constraint for sparse novel view synthesis that improves 3D reconstruction quality from limited input images. This learning-free method enhances existing NeRF and Ga…
-
EDoF-NeRF enhances depth-of-field for photorealistic neural radiance fields
Researchers have developed EDoF-NeRF, a novel method to enhance the depth-of-field (DoF) in neural radiance fields (NeRF) for more photorealistic novel view rendering. This technique utilizes a coded aperture placed at …
-
Shanghai Jiao Tong U. advances SLAM for dynamic, deformable environments
Researchers at Shanghai Jiao Tong University, led by Professor Hesheng Wang, are advancing Simultaneous Localization and Mapping (SLAM) beyond static environments. Their work focuses on enabling robots to navigate and u…