#3D reconstruction (28)

Waterfall Pagination

0:27

image-to-3d-pipeline: A Fair Benchmark and Browser Explorer for Image-to-3D Models

A fixed-protocol harness for comparing image-to-3D models. One set of AI renders of a fictional submersible goes into TRELLIS V1/V2 and TripoSR; each mesh is inspected through an identical Blender 4.3 EEVEE orbit and scored on a 0-2 five-axis rubric, then the winner ships into a Three.js + three-mesh-bvh explorer with real collision. TRELLIS V2 stochastic ranks first at 1.56 MB / 11,866 faces.

TRELLISTripoSRHunyuan3D

JavaScript258200

1:26

World Labs Atlas: a world model for spatial intelligence

@theworldlabs · 307 views · 2026-09-01

AtlasWorld LabsWorld Models

0:39

Lucida: Indoor Video to Editable 3D Scenes

@wildmindai · 157 views · 2026-09-01

Real-to-SimVLM3D reconstruction

3:33

DeepMind D4RT turns a video into a 4D world

@Alacritic_Super · 279 views · 2026-08-31

D4RT4D WorldWorld Models

0:16

ABot-Recon turns driving video into 3D scenes

@HuggingApps · 236 views · 2026-08-31

ABot-Recon3D reconstructionSpatial AI

3:53

Lumera turns an image into an editable UE5 world with meshes, lights, and layouts

@HaoZhao_AIRSUN · 335 views · 2026-08-29

3D reconstructionUnreal EngineUE5

0:15

ABot-Recon Streaming 3D Reconstruction

@IndieDevHailey · 209 views · 2026-08-29

SLAMAMapABot-Recon

0:58

LiteReality-Agent turns room scans into interactive 3D scenes

@ZheningHuang · 115 views · 2026-08-07

LiteRealityRGB-DScene Reconstruction

0:30

Insta360 X6: Spatial Capture turns 360 recordings into 3D Gaussian Splat scenes

@justinryanio · 112 views · 2026-08-07

Insta360Gaussian SplattingSpatial Capture

0:53

VidMap: Exploiting temporal structure for video-based Structure-from-Motion

@zador_pataki · 163 views · 2026-08-07

SLAMSfMECCV2026

0:34

DJI M4E and PortalCam air-ground 3DGS map fusion

@DuckbillStudio · 102 views · 2026-08-07

3D Gaussian SplattingDJI Matrice 4EPortalCam

StreamSplat: Streaming Feed-Forward 3D Gaussian Splatting

Feed-forward 3D Gaussian Splatting enables efficient novel-view synthesis without per-scene optimization, but most existing methods assume a fixed set of context views and process them jointly. This limits their applicability to online scenarios where calibrated views arrive sequentially and the scene must be updated causally. We present StreamSplat, a streaming feed-forward 3DGS framework that incrementally maintains a persistent geometry-grounded scene state and decodes it into renderable 3D Gaussians after each input chunk. StreamSplat centers on a Voxel-Aligned Causal Cache (VACC), which stores historical 3D tokens in a memory-bounded voxel structure so that memory grows with explored scene geometry rather than stream length. To better reuse history during causal prediction, we introduce History-Projected Depth Anchoring (HPDA) to project cached geometry as depth guidance for current cost-volume estimation, and Cache-Guided Feature Injection (CGFI) to inject cached latent evidence into Gaussian-token regression. Experiments on DL3DV, RealEstate10K, and ScanNet show that StreamSplat remains competitive with state-of-the-art feed-forward 3DGS methods under sparse causal inputs, despite not using future views or full-scene context. More importantly, it scales to long input streams with 256, 512, and 1024 views where fixed-view baselines run out of memory, yielding sustained improvements in novel-view synthesis quality as more observations arrive. The code will be made publicly available upon acceptance.

Changhao Song, Yuxuan Wang, Qibiao LiAug 3, 2026

3D Gaussian Splatting3D reconstructionStreaming InferenceAug 3, 2026

SLAMFormer-∞: Infinite SLAM Transformer for Unbounded Frontend and Backend Processing

We introduce the Infinite SLAM Transformer (SLAMFormer-∞), the first geometric transformer capable of supporting both long-range frontend and backend processing without an explicit distance bound. Instead of relying on a first-frame-anchored formulation, SLAMFormer-∞ employs memory conditions to define flexible coordinate systems and scales for input frames, enabling more expressive structural conditioning. Built upon this formulation, the frontend preserves efficient local computation, while the backend jointly optimizes long-range trajectories and scene geometry in a globally consistent manner. Experimental results demonstrate that SLAMFormer-∞ achieves superior or highly competitive performance in both trajectory estimation and scene reconstruction across large-scale datasets. Notably, SLAMFormer-∞ generalizes to extremely long trajectories, successfully operating on sequences exceeding 17km.

Zhijian Fang, Weicheng Zheng, Yijun YuanAug 4, 2026

SLAM3D reconstructionTransformerAug 4, 2026

1:40

Glob3R: Global Structure-from-Motion With 3D Foundation Models

@rsasaki0109 · 108 views · 2026-07-31

SfMStructure-from-Motion3D foundation model

0:37

Phone Video to Walkable 3D World in Real-Time

@heyrobinai · 101 views · 2026-07-30

Depth Anything3D Gaussian SplattingReal-Time

0:36

Neural Harmonic Textures: Real-Time Novel View Synthesis

@Arcanous98 · 122 views · 2026-04-09

Novel view synthesis3D Gaussian SplattingNeRF

NSL-SLAM: High-Fidelity Neural Structured-Light Depth for Practical SLAM and Reconstruction

Structured-light (SL) cameras power depth sensing in millions of devices, and recent neural SL decoding methods have substantially improved their depth quality. SLAM systems can benefit greatly from such strong depth sensing, where reliable geometry enables stable tracking and faithful reconstruction. In this work, we present NSL-SLAM, a practical SLAM system tailored for high-fidelity structured-light depth. We first strengthen SL depth sensing: inspired by the neural structured-light (NSL) method, we further incorporate strong monocular depth priors into the SL stereo decoding, reducing depth RMSE by 35% on Replica-SL compared to NSL. We then build a depth-centric SLAM pipeline with this stronger depth: because structured-light geometry is dense and metrically accurate, we keep it as the primary tracking signal, and add only sparse visual correspondences for geometrically degenerate cases and lightweight bundle adjustment for long-range drift. Our depth estimator and SLAM design reinforce each other: stronger depth makes a simple SLAM pipeline effective, and the depth-centric pipeline ensures this advantage transfers to downstream reconstruction. Experimentally, on the synthetic Replica-SL benchmark, NSL-SLAM achieves the best tracking accuracy and improves reconstruction F-score by 1.6 points over the SOTA baseline under a shared-depth protocol. On a real benchmark of 8 challenging scenes, it is the only method that avoids catastrophic failure on all sequences while achieving 43.3% lower trajectory deviation than selected baselines. The SLAM system runs online at 20.9 FPS, demonstrating that stronger structured-light depth and depth-centric system design together enable practical, robust SLAM.

Jiaheng Li, Binsheng Zhang, Xinhai ChangJul 27, 2026

SLAMStructured Light DepthNeural Depth EstimationJul 27, 2026