3D reconstruction

Bilibili Tech

Nov 1, 2023 · Artificial Intelligence

Neural Radiance Fields and Generative Intelligent Media: Recent Advances and Applications

Professor Hu Qiang presented recent progress in Neural Radiance Fields—covering implicit/explicit representations, hybrid models, and solutions for dynamic scenes, cloud‑based and edge‑cloud rendering—while also reviewing generative AI advances such as diffusion‑based text‑to‑image/video/3D, LoRA fine‑tuning, and large‑scale story‑book datasets, highlighting applications in virtual‑real content, smart‑city modeling, and 6‑DoF e‑commerce displays.

3D reconstructionNeural Renderingdiffusion models

0 likes · 14 min read

Neural Radiance Fields and Generative Intelligent Media: Recent Advances and Applications

DataFunTalk

Sep 28, 2023 · Artificial Intelligence

Panoramic Image Indoor Layout Estimation Using Vision Transformer (PanoViT)

This article introduces the PanoViT method for indoor layout estimation from panoramic images, covering research background, the transformer‑based architecture with backbone, vision transformer encoder, boundary‑enhancement and 3D loss modules, experimental results, and step‑by‑step usage in ModelScope.

3D reconstructioncomputer visiondeep learning

0 likes · 7 min read

Panoramic Image Indoor Layout Estimation Using Vision Transformer (PanoViT)

DataFunSummit

Aug 24, 2023 · Artificial Intelligence

Panoramic Indoor Layout Estimation with Vision Transformer (PanoViT)

This article introduces the PanoViT model, a vision‑transformer‑based approach for indoor layout estimation from panoramic images, covering its research background, architectural components, experimental results on public datasets, and step‑by‑step usage within ModelScope.

3D reconstructionModelScopecomputer vision

0 likes · 8 min read

Panoramic Indoor Layout Estimation with Vision Transformer (PanoViT)

DaTaobao Tech

Jun 14, 2023 · Artificial Intelligence

Optimizing NeRF for Real-Time Mobile 3D Rendering in Alibaba's Object Drawer

Alibaba’s Taobao engineers detail how they transformed slow, high‑quality NeRF reconstruction into a real‑time mobile solution by combining an Octree‑Tiny‑MLP architecture, SNeRG optimizations, and a high‑frequency voxel reduction that shrank models to ~5 MB and achieved ~6 FPS on low‑end Android phones, targeting sub‑1 MB models and 50 FPS.

3D reconstructioncomputer visionmobile optimization

0 likes · 10 min read

Optimizing NeRF for Real-Time Mobile 3D Rendering in Alibaba's Object Drawer

DaTaobao Tech

Feb 20, 2023 · Mobile Development

AR Foot Measurement and Hand Try-On Algorithms for Mobile Vision

The article presents a mobile‑vision solution that combines lightweight detection, line detection, segmentation and 3‑D point‑cloud reconstruction to measure foot length within 3 mm error, and a MANO‑based hand‑try‑on system that predicts full mesh vertices for real‑time watch, phone and ring fitting on smartphones.

3D reconstructionARFoot Measurement

0 likes · 18 min read

AR Foot Measurement and Hand Try-On Algorithms for Mobile Vision

DaTaobao Tech

Jun 10, 2022 · Artificial Intelligence

NeRF-Editing: Geometry Editing of Neural Radiance Fields

NeRF‑Editing introduces an interactive framework that lets users freely deform the geometry of neural radiance fields by coupling an explicit mesh with implicit NeRF representations, propagating mesh vertex changes through tetrahedral ARAP optimization to bend rays during rendering, enabling realistic edits and animations on synthetic and real‑world scenes, a first reported at CVPR 2022.

3D reconstructionARAP deformationNeural Rendering

0 likes · 6 min read

NeRF-Editing: Geometry Editing of Neural Radiance Fields

DaTaobao Tech

Apr 28, 2022 · Artificial Intelligence

WCPA 2022: 3D Human Body and Face Reconstruction Competition

The inaugural WCPA 2022 workshop and challenge, co‑organized by Alibaba Taobao Technology, HaiTian RuiSheng, the Chinese Academy of Sciences’ Institute of Automation and the University of Parma at ECCV 2022, invites participants to develop multi‑view algorithms for 3D human‑body and face reconstruction using the MVP‑Human dataset, with two competition tracks, a June submission deadline, July results, and prize details provided.

3D reconstructionAI competitionFace Reconstruction

0 likes · 7 min read

WCPA 2022: 3D Human Body and Face Reconstruction Competition

DaTaobao Tech

Mar 21, 2022 · Artificial Intelligence

Neural Rendering Based 3D Modeling and Multi‑Video Visual Localization for E‑commerce

The paper presents Object Drawer, a Taobao Tech system that uses neural‑rendering and a SuperPoint‑SuperGlue‑based SfM pipeline—enhanced by sparse sampling, loop constraints, frame‑skipping, and a novel 2D‑matching‑3D‑solving alignment across multiple videos—to achieve 99.3% visual‑localization success and high‑quality 3‑D reconstructions with pixel‑accurate segmentation for e‑commerce displays.

3D reconstructionMulti-view Pose AlignmentNeural Rendering

0 likes · 9 min read

Neural Rendering Based 3D Modeling and Multi‑Video Visual Localization for E‑commerce

Kuaishou Tech

Sep 17, 2021 · Artificial Intelligence

SnowflakeNet: Point Cloud Completion by Snowflake Point Deconvolution with Skip-Transformer

SnowflakeNet introduces a novel Snowflake Point Deconvolution architecture combined with a Skip-Transformer to progressively split seed points, enabling high‑quality point‑cloud completion that preserves fine‑grained geometric details such as smooth surfaces, sharp edges, and corners across dense and sparse datasets.

3D reconstructionSnowflakeNetcomputer vision

0 likes · 10 min read

SnowflakeNet: Point Cloud Completion by Snowflake Point Deconvolution with Skip-Transformer

Kuaishou Tech

Jun 21, 2021 · Artificial Intelligence

Kuaishou’s CVPR 2021 Paper Highlights: 3D Vision, Domain Adaptation, Point Cloud Completion, Video Segmentation, and Face Forgery Detection

Kuaishou secured 14 accepted papers at CVPR 2021, spanning 3D hand mesh recovery, unsupervised keypoint detection, point cloud completion, modular interactive video segmentation, deep video matting, co‑salient object detection, occlusion‑aware instance segmentation, semantic image matting, and face forgery detection, showcasing the maturity of its research collaborations.

3D reconstructionCVPRFace Forgery Detection

0 likes · 14 min read

Kuaishou’s CVPR 2021 Paper Highlights: 3D Vision, Domain Adaptation, Point Cloud Completion, Video Segmentation, and Face Forgery Detection

Kuaishou Tech

Apr 16, 2021 · Artificial Intelligence

Camera-Space Hand Mesh Recovery via Semantic Aggregation and Adaptive 2D-1D Registration

Camera-space hand mesh recovery (CMR) leverages semantic aggregation of 2D cues and adaptive 2D‑1D registration to predict absolute 3D hand pose and shape directly in camera coordinates, improving accuracy on benchmarks such as FreiHAND, RHD, and Human3.6M.

2D-1D registration3D reconstructioncamera space

0 likes · 17 min read

Camera-Space Hand Mesh Recovery via Semantic Aggregation and Adaptive 2D-1D Registration

Didi Tech

Sep 10, 2020 · Artificial Intelligence

Technical Overview of DiDi's AR Indoor Navigation System

DiDi's AR indoor navigation system addresses GPS unreliability in large indoor venues by using SfM-based 3D reconstruction, robust visual localization with magnetometer/GNSS priors, and sensor fusion with pedestrian dead‑reckoning and deep‑learning heading estimation, cutting passenger pick‑up time by up to 25 % across dozens of airports and malls.

3D reconstructionAR navigationIndoor Positioning

0 likes · 19 min read

Technical Overview of DiDi's AR Indoor Navigation System