애플 AI 모델 LiTo, 사진 한 장으로 3D 물체를 구현하는 원리 - No Worry Be Happy 최근 애플 연구진이 발표한 LiTo 모델은 단 한 장의 사진만으로도 3D 객체의 기하학적 형태와 조명 효과까지 완벽하게 재구성합니다. 지금까지 3D 모델링을 위해 여러 각도에서 찍은 수많은 데이터가 필요했던 과거의 방식과는 차원이 다른 변화입니다. 사진 한 장 속에 담긴 정보만으로

애플 AI 모델 LiTo, 사진 한 장으로 3D 물체를 구현하는 원리

https://bit.ly/3PmrVwC

#AppleAI #LiToModel #SingleImage3D #3DReconstruction #AIModel #GeometryReconstruction #LightingEffects

The results of 3D reconstructions using an explicit correction of the number of overrepresented and underrepresented projections for non-uniformly distributed sets are reported #CryoEM #3DReconstruction #ViewFrequency doi.org/10.1107/S205...

Apple's new AI model reconstructs 3D objects with realistic lighting from a single image, revolutionizing AR, VR, and more. #AppleAI #3DReconstruction #MachineLearning #TechInnovation Link: thedailytechfeed.com/apple-unveil...

¡Revolución en la reconstrucción 3D! NVIDIA presenta PPISP, la solución definitiva a los errores de luz y color en NeRF y Gaussian Splatting. Logra realismo extremo con control de exposición inteligente. 📸✨
youtu.be/XgyPzjCuAKs
#NVIDIA #AI #3DReconstruction #NeRF #PPISP #IA

Dataset Sample - Realistic Khachkar

SHREC 2026: Reconstruct high-frequency geometry from 90 views (COLMAP poses).

Dataset out now.

Registration → cllull@dcc.uchile.cl. Submissions due Apr 3, 2026.

Details: shapevision.dcc.uchile.cl/cllull-shrec2026

#ComputerVision #3DReconstruction #Photogrammetry

GaMO: Geometry-aware Multi-view Diffusion Outpainting for Sparse-View 3D Reconstruction
Chin-Yang Lin, Hao-Jen Chien et al.
Paper
Details
#3DReconstruction #DiffusionModel #MultiView

CSMBR-ATLOMY Conference

Thank you to the organisers and attendees for two wonderful days of inspiring presentations, questions, and debates!

#CSMBR #ATLOMY #3DReconstruction #AncientAnatomy #MedicalHistory

WINTER TALES AT THE DOMUS COMELIANA

Heading towards the conclusion of the wonderful two-day ATLOMY conference at the CSMBR, we share a few shots of the leaning tower from the upper terrace of the Domus Comeliana.

#CSMBR #ATLOMY #3DReconstruction #AncientAnatomy #MedicalHistory

CSMBR-ATLOMY Conference

TECHNICAL KNOWLEDGE IN HUMAN HISTORY

After an enthusiastic beginning, yesterday, a second day of insightful presentations and discussions awaits our attendees.
#CSMBR #Atlomy #Anatomy #3Dreconstruction

Meta’s Releases SAM 3D Turns A Single Photo Into A Full 3D Model In Seconds Meta debuts SAM 3D, a new AI model that turns a single photo into a full 3D object — reshaping AR, design, robotics, and global computer vision.

Meta just dropped SAM 3D — and it’s WILD.
One photo → a full 3D model. No scans. No rigs. No fancy setup.

Creators, AR devs, robotics geeks… this update is pure chaos fuel.
The 3D future? 🚀✨

#SAM3D #MetaAI #3DReconstruction #AInews #TechDrop #NextGenAI #AI

evolutionaihub.com/meta-sam-3d-...

Three-dimensional reconstruction from CT scans maps hernia boundaries, identifies contents, and reveals anatomy critical for safe dissection during complex repairs.

#3DReconstruction #SahajHospitalIndore #DetailedMapping #SafeSurgery

Original post on det.social

Europeana’s EUreka3D is reconstructing Europe’s cultural legacy in 3D and making it interoperable across institutions.
By merging archives, models, and metadata, it’s turning scattered memory into a shared spatial archive, usable for research, education, and public storytelling […]

"Stereo Hand-Object Reconstruction for Human-to-Robot Handover"

Y. L. Pang, A. Xompero, C. Oh, A. Cavallaro
IEEE Robotics and Automation Letters, Vol.10, n.6, June 2025

📝Article: doi.org/10.1109/LRA....

#robotics #ai #computervision #handover #grasping #manipulation #3Dreconstruction

New AI model turns photos into explorable 3D worlds, with caveats https://arstechni.ca #3Dreconstruction #depthestimation #machinelearning #scenegeneration #computervision #videosynthesis #3Dgeneration #generativeai #multimodalAI #worldmodels #AIresearch #opensource #Aivideo #Tencent #Biz&IT…

From Slices to Structures: Unsupervised 3D Reconstruction of Female
Pelvic Anatomy from Freehand Transvaginal Ultrasound
Ece Ozkan, Fabian Laumer et al.
Paper
Details
#3DReconstruction #MedicalImaging #UltrasoundAnatomy

#MasterThesis opportunity "3D Shape Completion for Individualized Implant Design" @ ZIB research group "Computational Diagnosis and Therapy Planning"
#MedicalImaging #3DReconstruction #DeepLearning #NumericalMathematics
www.zib.de/thesis/3d-sh...

New resource: You can now see demo videos of our AI services for game developers on the Results page of our website!

👉 Check out the demos on our website: mementoes.eu/results/

#AI #DigitalHeritage #3DReconstruction #SuperResolution #StyleTransfer #Gamedev #indiedev

🚀More good news: our paper SE-GS is accepted as an oral at ICCV 2025 🥳📸

Gaussian Splatting gets another boost 🌈
Code’s out, camera-ready coming soon!
🔗 lnkd.in/gprqxNjq
#ICCV2025 #GaussianSplatting #3DVision
#3Dreconstruction #rendering

Point3R: Streaming 3D Reconstruction with Explicit Spatial Pointer
Memory
Jie Zhou, Jiwen Lu et al.
Paper
Details
#3DReconstruction #SpatialMemory #Point3RTechnology

Original post on det.social

GaVS: 3D-Grounded Video Stabilization via Temporally-Consistent Local Reconstruction
GaVS reformulates video stabilization as a 3D task: using temporally-consistent local reconstructions and Gaussian Splatting, it stabilizes full-frame video with high geometric consistency and robustness to […]

Made some Roman lectus beds. These were used for lounging, dining, or sleeping, often adorned with cushions, headrests, and even bronze or ivory fittings. In these renders, I recreated the elegant simplicity of Roman beds, perfect for a midday nap.
#AncientArt #3DReconstruction #AncientColor

RDD: Robust Feature Detector and Descriptor using Deformable Transformer As a core step in structure-from-motion and SLAM, robust feature detection and description under challenging scenarios such as significant viewpoint changes remain unresolved despite their ubiquity. While recent works have identified the importance of local features in modeling geometric transformations, these methods fail to learn the visual cues present in long-range relationships. We present Robust Deformable Detector (RDD), a novel and robust keypoint detector/descriptor leveraging the deformable transformer, which captures global context and geometric invariance through deformable self-attention mechanisms. Specifically, we observed that deformable attention focuses on key locations, effectively reducing the search space complexity and modeling the geometric invariance. Furthermore, we collected an Air-to-Ground dataset for training in addition to the standard MegaDepth dataset. Our proposed method outperforms all state-of-the-art keypoint detection/description methods in sparse m

🤖✨ unlock new levels of keypoint detection and description with rdd, using deformable transformers to handle tough viewpoints and achieve superior 3d reconstruction performance
https://arxiv.org/abs/2505.08013v1
#featuredetection #transformers #3dreconstruction #deeplearning #slam

🧱 Ready to build the past in 3D?

Join our Summer School on 3D Reconstruction – a hands-on week of digital archaeology, modeling & photogrammetry.

📍 Brno | 📅 Sept 15–19
📝 Apply by May 31
🔗 Apply here: bit.ly/43hBu4f

#3DReconstruction #DigitalHeritage #SummerSchool2025

Reconstructions of finds from Sutton Hoo - The Time Team Dig: Part 2 - by Shadow Tor.

Watch here: youtu.be/ExNijhLqjT4?...

Part 3 tonight on YouTube

#suttonhoo #3dfinds #digitalarchaeology #3dreconstruction #nationaltrust #timeteam #archaeology #suttonhooarchaeology @timeteam.bsky.social

Reconstructions of finds from Sutton Hoo - The Time Team Dig: Part 2 - by Shadow Tor.

Watch here: youtu.be/ExNijhLqjT4?...

Part 3 screens tonight on YouTube

#suttonhoo #3dfinds #digitalarchaeology #3dreconstruction #nationaltrust #timeteam #archaeology #anglosaxon #suttonhooarchaeology

TC3DGS Temporally Compressed 3D Gaussian Splatting for Dynamic Scenes

Had a great time giving a talk at Magic Leap on "Real-Time Dynamic 3D Scenes: Temporal Compression of Gaussian Representations"!

Shared our TC3DGS work and exciting future directions in 3D vision! 🚀

🌐 ahmad-jarrar.github.io/tc-3dgs/

#3DReconstruction #GaussianSplatting #ComputerVision #ARVR

"𝘗𝘳𝘦𝘴𝘦𝘳𝘷𝘪𝘯𝘨 𝘵𝘩𝘦 𝘱𝘢𝘴𝘵, 𝘰𝘯𝘦 𝘭𝘢𝘺𝘦𝘳 𝘢𝘵 𝘢 𝘵𝘪𝘮𝘦."
𝗥𝗘𝗖𝗥𝗘𝗔𝗧𝗜𝗡𝗚 𝗔𝗥𝗧𝗜𝗙𝗔𝗖𝗧𝗦 𝗜𝗡 𝟯𝗗
Museums and galleries recreate rare and irreplaceable objects in 3D.

#MuseumTech #CulturalHeritage #3DReconstruction #DigitalPreservation #3DForMuseums #GalleryTech #ArtTech #3DPrinting #3DModeling #3DArt #3Dprintai

#Researchers create #3DModel of #ancient #StoneSculpture from a single 134-year-old #photo zorz.it/VrKxk | #MattGrowcoot #3DReconstruction #ArtificialIntelligence #ComputerVision #NeuralNetwork #scientists #RitsumeikanUniversity #CulturalHeritage

MUSt3R: Multi-view Network for Stereo 3D Reconstruction DUSt3R introduced a novel paradigm in geometric computer vision by proposing a model that can provide dense and unconstrained Stereo 3D Reconstruction of arbitrary image collections with no prior info...

🧵 2/9
MUSt3R: Multi-view Network for Stereo 3D Reconstruction
We enhance stereo 3D recon with multi-view inputs, boosting efficiency for SfM & odometry. Cabon et al. #3DReconstruction 📄 Paper: arxiv.org/abs/2503.01661