3D computer graphics
PulseAugur coverage of 3D computer graphics — every cluster mentioning 3D computer graphics across labs, papers, and developer communities, ranked by signal.
5 day(s) with sentiment data
-
GENA3D framework integrates 2D priors with 3D reasoning for amodal 3D modeling
Researchers have developed GENA3D, a novel framework for generating complete 3D object models from incomplete visual data. This approach effectively bridges the gap between 2D generative priors, which offer strong appea…
-
SpatialSV framework enhances MLLMs' 3D spatial awareness with interpretable visual supervision
Researchers have introduced SpatialSV, a novel framework aimed at enhancing the 3D spatial awareness of multimodal large language models (MLLMs). Unlike existing methods that rely on external tools or opaque feature dis…
-
S-Agent framework enhances VLMs for 3D spatial reasoning · 4 sources tracked
Researchers have introduced S-Agent, a novel framework designed to enhance visual language models (VLMs) for spatial reasoning in 3D environments. S-Agent integrates temporal memory and a hierarchy of spatial tools to e…
-
Tuzhu Technology Sells Over 1 Million Consumer 3D Printers
Tuzhu Technology has announced a significant milestone, surpassing one million cumulative sales of its consumer-grade 3D printers in the domestic market. This achievement positions Tuzhu as the first brand in the indust…
-
Surflo Model Achieves Flexible 3D Surface Reconstruction via Flow Matching
Researchers have introduced Surflo, a novel 3D surface reconstruction model that processes unposed RGB views into a global latent state. This approach allows for the decoding of oriented 3D surface points through flow m…
-
Orbita-Light stock surges amid AI development clarification
The company Orbita-Light announced that its stock price has deviated significantly over three consecutive trading days, with cumulative gains exceeding 30%. Orbita-Light's core business involves the design, development,…
-
Gaga framework uses 3D memory bank for scene segmentation
Researchers have developed Gaga, a novel framework for reconstructing and segmenting 3D scenes using inconsistent 2D masks from zero-shot segmentation models. Unlike previous methods that relied on object tracking or co…
-
3D Workflows Enhance AI Image Generation with Spatial Control
This article explores the integration of 3D modeling techniques with AI image and video generation to overcome limitations in spatial control. It details how 3D assets like blockouts, depth maps, and normal maps can pro…
-
AI 3D tools need product-specific evals, not just benchmarks
When developing AI-powered 3D tools, relying solely on public benchmarks for model selection is insufficient. These benchmarks often test for basic functionality like code generation or simple object creation, which doe…
-
3D MRI segmentation framework reveals distinct optimization needs for 2D vs 3D models
Researchers have developed a novel weakly supervised learning framework for segmenting 3D MRI data, addressing the challenge of limited volumetric annotations. Their study reveals that techniques beneficial for 2D model…
-
UniCorrn Transformer unifies 2D and 3D geometric matching across modalities
Researchers have introduced UniCorrn, a novel Transformer-based model designed to unify geometric matching across various visual data types. This model can handle correspondence tasks between 2D images, 2D images and 3D…
-
AI advancements span robot manufacturing, dev tools, and cost-effective models
A discussion is emerging around the potential for integrated model handoff stacks to serve as new Integrated Development Environments (IDEs), particularly for multimodal workflows involving image, vision, and 3D models.…
-
COMMA network enhances 3D dispersed vessel segmentation with coordinate awareness
Researchers have developed a new network architecture called COMMA for segmenting 3D dispersed blood vessels in medical imaging. This Coordinate-aware Modulated Mamba Network utilizes both global and local branches to m…
-
3DTeethLand challenge spurs AI advances in dental landmark detection
The 3DTeethLand challenge, held at MICCAI 2024, aimed to advance deep learning techniques for detecting dental landmarks from 3D intraoral scans. This challenge provided a new dataset of 340 scans to benchmark algorithm…