Tagged articles
Gaussian Splatting
11 articles · Page 1 of 1
Zero-HLM, a Real2Sim2Real framework from BIGAI, BIT, Tsinghua, and Deta, reconstructs real scenes via Gaussian splatting and GPT-Astra, then generates and validates whole-body humanoid demonstrations in simulation, expanding 45 source demos into 4,800 executable trajectories that enable zero-shot transfer to a Unitree G1 with 69% success across five generalization settings, outperforming real-data baselines (23%).
GPT-AstraGaussian SplattingHumanoid Robot
0 likes · 13 min read

Peking University's DragMesh enables interactive 3D articulated motion generation on existing assets by predicting joint parameters from a single drag, generating dual quaternion trajectories via a non-autoregressive transformer, and transferring motion to both mesh and 3D Gaussian Splatting representations, achieving real-time performance on GAPartNet.
3D generationDragMeshGAPartNet
0 likes · 13 min read

Peking University, VGI Labs, and UC Merced introduce DynStream, a feed-forward framework that reconstructs dynamic 3D scenes from pose-free video streams by chunking input, predicting relative poses and scale factors for global alignment, and separating static and dynamic Gaussians for continuous rendering.
4D reconstructionComputer VisionGaussian Splatting
0 likes · 9 min read

The Oxygen XR team and Tsinghua University propose DirectFisheye‑GS, a framework that embeds a fisheye camera model directly into the 3D Gaussian splatting pipeline and introduces cross‑view joint optimization, eliminating distortion and view‑inconsistency while achieving SOTA performance on multiple public datasets with efficient rendering and reconstruction.
3D ReconstructionComputer VisionCross-View Optimization
0 likes · 11 min read

The DirectFisheye‑GS framework embeds a fisheye camera model directly into the 3D Gaussian splatting pipeline and introduces cross‑view joint optimization, eliminating shape distortion and inter‑view inconsistencies, achieving SOTA performance on multiple public datasets while remaining compatible with existing 3DGS toolchains.
3D ReconstructionCVPR 2026Cross-View Optimization
0 likes · 10 min read

Researchers from Insta360, Wuhan University and Sun Yat‑sen University introduce PanoLOG, a two‑stage Gaussian‑splatting framework that replaces visibility‑based partitioning with gradient‑based criteria, enabling efficient, high‑quality 3D reconstruction from panoramic images and achieving state‑of‑the‑art results on Pano360, Ricoh360 and 360Roam datasets.
Computer VisionGaussian SplattingPanoLOG
0 likes · 12 min read


SuanNiApr 15, 2026 · Industry Insights
Spark 2.0 is an open‑source WebGL2‑based rendering engine that uses continuous LoD trees, a custom RAD file format, and GPU memory virtualization to stream and display massive 3D Gaussian‑splatting scenes on phones, tablets and browsers with smooth, real‑time interaction.
3D renderingBrowser graphicsGaussian Splatting
0 likes · 13 min read


AntTechFeb 10, 2026 · Artificial Intelligence
Split4D introduces a novel paradigm for 4D scene reconstruction that eliminates the need for video segmentation by leveraging single‑frame 2D masks, a freetime feature learning strategy, streaming sampling, and 3D tracking regularization, achieving high‑quality, object‑level decoupled representations across complex dynamic scenarios.
4D reconstructionAI graphicsGaussian Splatting
0 likes · 8 min read

SplatSSC introduces a depth‑guided Gaussian splatting framework that replaces random primitive initialization with geometry‑aware priors and a decoupled aggregation module, achieving state‑of‑the‑art performance on indoor semantic scene completion while dramatically reducing computational overhead and eliminating floaters.
3D PerceptionAI researchGaussian Splatting
0 likes · 10 min read

This article explains how 3D Gaussian Splatting transforms ordinary video footage into high‑quality 3D reconstructions with minimal equipment, outlines the low‑cost workflow using ffmpeg and COLMAP, and discusses practical challenges and future possibilities for the technology.
3D ReconstructionCOLMAPComputer Vision
0 likes · 5 min read

This article explains how to create high‑quality 3D scenes from ordinary video footage by slicing frames with ffmpeg, extracting camera poses with COLMAP, and applying 3D Gaussian Splatting to replace traditional mesh‑texture pipelines, dramatically lowering equipment costs and data size.
3D ReconstructionCOLMAPComputer Vision
0 likes · 6 min read
