3D foundation models
PulseAugur coverage of 3D foundation models — every cluster mentioning 3D foundation models across labs, papers, and developer communities, ranked by signal.
4 day(s) with sentiment data
-
New framework enables category-agnostic 3D shape editing
Researchers have developed CNS-Edit++, a framework for editing 3D shapes in a category-agnostic manner. This method utilizes a coupled neural shape representation, combining a global latent code for semantic understandi…
-
3D Foundation Models revolutionize plant phenotyping, slashing reconstruction time
Researchers have developed a new framework for 3D plant phenotyping that leverages 3D Foundation Models (3DFMs) to significantly accelerate the reconstruction process. This approach replaces traditional methods like COL…
-
New framework adapts 3D models for satellite multi-view reconstruction
Researchers have developed EO-VGGT, a new framework designed to adapt existing 3D foundation models for satellite multi-view reconstruction. This framework addresses the geometric discrepancies between implicit perspect…
-
New EPO framework boosts 3D foundation model accuracy without feature extraction
Researchers have developed a new framework called Edge-based Pose Optimization (EPO) to enhance the accuracy of 3D foundation models. Unlike traditional methods that require extensive feature extraction and matching, EP…
-
Local AI Tools Emerge: Offline Dictation, 3D Models, GPU Acceleration & Mac Containers
This week's AI news highlights tools and techniques for enhancing local AI deployments. FluidVoice offers fast, private, offline dictation on macOS, while a new 3D foundation model reconstructs scenes from streaming dat…
-
New 3D Optimization Framework Enhances Video Depth Estimation
Researchers have developed a novel 3D consistency optimization framework for self-supervised monocular video depth estimation. This new approach treats sequential video depth estimation as a multi-view 3D reconstruction…
-
GeoVR framework adds 3D spatial awareness to multimodal LLMs
Researchers have developed GeoVR, a new framework designed to imbue multimodal large language models (MLLMs) with 3D spatial awareness. This is achieved by distilling geometric knowledge from existing 3D foundation mode…
-
New method enhances fine-tuning of 3D foundation models
Researchers have developed a new method for efficiently fine-tuning 3D foundation models, addressing the challenges posed by variations in texture, geometry, camera motion, and lighting. The approach involves generating…
-
PaGeR framework adapts 3D models for 360-degree panoramic scene reconstruction
Researchers have developed PaGeR, a framework that adapts existing 3D foundation models, originally designed for perspective images, to reconstruct full 360-degree scenes from single panoramic images. This approach allo…