Nerf
PulseAugur coverage of Nerf — every cluster mentioning Nerf across labs, papers, and developer communities, ranked by signal.
- subsidiary of Hasbro 100%
- subsidiary of Parker Brothers 100%
- instance of ScienceCast 90%
- instance of Gotit.pub 90%
- instance of CatalyzeX 90%
- instance of alphaXiv 90%
- instance of Neural radiance field 90%
- instance of CORE Recommender 90%
- used by alphaXiv 70%
- used by ScienceCast 70%
- used by CatalyzeX 70%
- used by Gotit.pub 70%
4 day(s) with sentiment data
-
AMD acquires Fei-Fei Li's World Labs for $8.2B to integrate AI models with hardware
AMD has acquired World Labs, a two-year-old company founded by AI pioneer Fei-Fei Li, for approximately $8.2 billion in an all-stock deal. This acquisition positions Li as AMD's Executive Vice President and Chief Scient…
-
New framework AutoPhyX generates physics properties from text for 3D objects
Researchers have developed AutoPhyX, a novel framework designed to automatically generate physics properties for 3D objects based on text descriptions. This system addresses the limitations of previous methods that reli…
-
New method aligns neural network weights, reducing barriers in NeRF models
Researchers have developed a new method called Progressive Permutation Alignment with Temperature-Controlled Spectral Sharpening to address the challenge of permutation symmetry in implicit neural representations (INRs)…
-
NeRF improved with self-supervised geometry regularization
Researchers have developed a new method to improve the geometric accuracy of Neural Radiance Fields (NeRF) by incorporating a self-supervised cross-ray consistency approach. This technique enhances the density field of …
-
EGGHead algorithm enhances single-image human head generation
Researchers have introduced EGGHead, a novel Gaussian allocation algorithm designed to improve the efficiency and generalizability of creating photorealistic human heads from single images. This method optimizes the ass…
-
DriftNeRF improves sparse-view Neural Radiance Fields by penalizing density disagreement
Researchers have developed DriftNeRF, a novel regularizer designed to improve the performance of Neural Radiance Fields (NeRF) when only a sparse set of input views is available. The method addresses a core limitation i…
-
DriveWorld3D framework enhances autonomous driving simulation with evidence-constrained 3D modeling
Researchers have introduced DriveWorld3D, a novel framework designed to enhance 3D world modeling and generative simulation for autonomous driving systems. This framework integrates temporal video learning with multi-se…
-
New 3D object removal method uses texture-space inpainting
Researchers have developed a new method called 3DTexMOR for removing multiple objects from 3D scenes reconstructed using 3D Gaussian splatting. This technique performs inpainting within a unified texture space, which pr…
-
MoonGS framework reconstructs lunar surfaces using Gaussian Splatting
Researchers have developed MoonGS, a novel 3D Gaussian Splatting framework designed for high-quality reconstruction of lunar surfaces from sparse rover images. This framework can generate photorealistic novel views in a…
-
DySurface framework bridges explicit Gaussians and implicit functions for dynamic scene geometry
Researchers have introduced DySurface, a new framework designed to improve the reconstruction of temporally consistent geometric surfaces in dynamic scenes. This method combines the strengths of explicit 3D Gaussian Spl…
-
New research explores 4D scene reconstruction techniques · 4 sources tracked
Four recent arXiv papers explore advancements in 4D scene reconstruction, a field focused on capturing evolving geometry, appearance, and motion from visual data. Sparc4D introduces a compact autoencoder for dynamic sce…
-
SVRecon framework enables high-resolution neural surface reconstruction
Researchers have introduced Sparse Volumetric Reconstruction (SVRecon), a novel framework for generalizable neural surface reconstruction. This method addresses the memory limitations of previous approaches by employing…
-
HKUST researchers blend AI with 3D geometry for enhanced visual consistency
Researchers from the Hong Kong University of Science and Technology, led by Professor Tan Ping, are exploring the integration of deep learning models with traditional 3D geometry techniques to enhance global consistency…
-
New NeRF framework reconstructs 3D coronary arteries from limited X-ray views
Researchers have developed NeCA++, a novel multi-stage neural radiance field (NeRF) framework designed for 3D coronary artery reconstruction from limited, narrow-angle X-ray angiographic projections. This self-supervise…
-
New benchmark EditBench3D evaluates 3D scene editing beyond semantic alignment
Researchers have introduced EditBench3D, a new benchmark designed to evaluate the editability of 3D scenes beyond simple semantic alignment. This benchmark assesses four key properties: instruction fidelity, spatial loc…
-
New Transformer Model Reconstructs 3D Curves from Sparse Images
Researchers have developed CGGT, a Curve-Grounded Geometry Transformer, designed to reconstruct editable 3D parametric curves from sparse, unposed multi-view images. This new method bypasses the need for dense camera vi…
-
JAX3D enables hierarchical NeRF for advanced 3D rendering and reconstruction
Researchers have developed a method for creating hierarchical Neural Radiance Fields (NeRFs) using JAX and the jax3d library. This approach enables volumetric rendering, novel-view synthesis, and 3D reconstruction. The …
-
New 3D Point Splatting Renderer Advances mmWave Radar Novel View Synthesis
Researchers have developed 3D Point Splatting (3DPS), a novel differentiable point renderer specifically designed for mmWave radar novel view synthesis. This new method addresses limitations in existing techniques by be…
-
PointSplat reduces 3D model redundancy for immersive streaming · 1 source tracked
Researchers from Zhejiang University, ByteDance, and The Chinese University of Hong Kong, Shenzhen have developed PointSplat, a novel method for creating more compact 3D human representations. This approach shifts from …
-
AccidentSim generates realistic vehicle collision videos from accident reports
Researchers have developed AccidentSim, a new framework designed to generate realistic vehicle collision videos for autonomous driving research. This system extracts physical clues and contextual information from real-w…