PulseAugur
EN
LIVE 21:33:15

New SAM 3D models enable single-image 3D reconstruction

By PulseAugur Editorial · [2 sources] ·

Researchers have introduced SAM 3D, a generative model capable of reconstructing 3D objects, including geometry and texture, from a single 2D image. This model is designed to handle complex real-world scenes with occlusions and clutter, achieving significant improvements over existing methods. A subsequent development, Fast-SAM3D, addresses the inference speed limitations of SAM 3D by introducing a training-free framework that dynamically adjusts computation based on generation complexity, achieving up to a 2.67x speedup with minimal loss in fidelity. AI

IMPACT These models advance single-image 3D reconstruction capabilities, potentially impacting fields requiring rapid 3D asset generation.

RANK_REASON The cluster contains two research papers detailing new models for 3D reconstruction from images.

Read on arXiv cs.AI →

AI-generated summary · Google Gemini · from 2 sources. How we write summaries →

New SAM 3D models enable single-image 3D reconstruction

How we ranked this

Signal score
0 / 100
Composite score across the factors below. Higher = stronger signal that this story matters right now.
Newsworthiness bucket
Research
The cluster contains two research papers detailing new models for 3D reconstruction from images.
Source corroboration
2 independent sources
Multiple independent publishers reporting the same story raises confidence that it's real and newsworthy.
Topics
paper, model release
Editorial topic classification. Feeds into how the story surfaces on /topic/<slug> hub pages and into the per-entity coverage mix.
AI-industry relevance
High
Clearly on-topic for AI-industry coverage.
Story freshness
128 days old
Aged out of breaking-news scoring windows; ranking reflects the durable signal from the full source set.

Full methodology in our editorial standards.

COVERAGE [2]

  1. arXiv cs.AI TIER_1 (TL) · SAM 3D Team, Xingyu Chen, Fu-Jen Chu, Pierre Gleize, Kevin J Liang, Alexander Sax, Hao Tang, Weiyao Wang, Michelle Guo, Thibaut Hardin, Xiang Li, Aohan Lin, Jiawei Liu, Ziqi Ma, Anushka Sagar, Bowen Song, Xiaodong Wang, Jianing Yang, Bowen Zhang, Piotr D… ·

    SAM 3D: 3Dfy Anything in Images

    arXiv:2511.16624v2 Announce Type: replace-cross Abstract: We present SAM 3D, a generative model for visually grounded 3D object reconstruction, predicting geometry, texture, and layout from a single image. SAM 3D excels in natural images, where occlusion and scene clutter are com…

  2. arXiv cs.CV TIER_1 English(EN) · Weilun Feng, Mingqiang Wu, Zhiliang Chen, Chuanguang Yang, Haotong Qin, Yuqi Li, Xiaokun Liu, Guoxin Fan, Libo Huang, Yulun Zhang, Michele Magno, Yongjun Xu, Zhulin An ·

    Fast-SAM3D: 3Dfy Anything in Images but Faster

    arXiv:2602.05293v2 Announce Type: replace Abstract: SAM3D enables scalable, open-world 3D reconstruction from complex scenes, yet its deployment is hindered by prohibitive inference latency. In this work, we conduct the \textbf{first systematic investigation} into its inference d…

RELATED ENTITIES

RELATED TOPICS