PulseAugur
EN
LIVE 10:21:33
ENTITY Google Scanned Objects

Google Scanned Objects

PulseAugur coverage of Google Scanned Objects — every cluster mentioning Google Scanned Objects across labs, papers, and developer communities, ranked by signal.

Show in brief
Total · 30d
3
6 over 90d
Releases · 30d
0
0 over 90d
Papers · 30d
2
5 over 90d
TIER MIX · 90D
TOPICS
SENTIMENT · 30D

1 day(s) with sentiment data

RECENT · PAGE 1/1 · 6 TOTAL
  1. TOOL · CL_354699 ·

    Hugging Face releases guide for fine-tuning 3D generation model TRELLIS.2

    Hugging Face has released a comprehensive guide detailing how to fine-tune TRELLIS.2, a 3D generation model. The guide focuses on using LoRA (low-rank adaptation) to improve specific aspects of 3D model generation, such…

  2. TOOL · CL_294764 ·

    PhysForge framework offers advanced material control in 3D asset generation

    Researchers have introduced PhysForge, a novel framework designed for enhanced control over material properties in 3D asset generation. This Video Diffusion Model-based system comprises two modules: PhysFit, which uses …

  3. TOOL · CL_280581 ·

    New AI method generates simulation-ready collision geometry from images

    Researchers have developed I2CD, a novel method for generating convex collision geometry directly from single RGB images. This approach bypasses the traditional, time-consuming pipeline of reconstructing 3D models and t…

  4. TOOL · CL_218308 ·

    New method uses spherical occupancy profiles for 3D reconstruction and generation

    Researchers have developed a novel method for 3D reconstruction and generation using spherical occupancy profiles, which represent ray-wise occupancy probabilities. This approach unifies discriminative and generative ta…

  5. TOOL · CL_204134 ·

    Owner3D framework enables training-free localized 3D stylization

    Researchers have introduced Owner3D, a novel framework designed for localized 3D stylization that operates without requiring additional training. This method integrates style control directly into the large reconstructi…

  6. RESEARCH · CL_98130 ·

    New VLM-Judge Protocol Evaluates 3D Mesh Quality Reliably

    Researchers have developed a de-biased protocol using vision-language models (VLMs) to evaluate the quality of 3D meshes generated from single images. This protocol, which involves using distinct VLM judges for training…