Scal3R Enables Stable Kilometer-Scale 3D Reconstruction of Long Videos

Scal3R introduces test‑time training with a global‑context memory and synchronization mechanism that lets models train on and infer over ultra‑long video sequences, achieving accurate camera poses and dense point clouds for kilometer‑scale scenes while outperforming prior SLAM, SfM and streaming baselines on multiple benchmarks.

3D ReconstructionScal3RTest-Time Training

0 likes · 11 min read

Scal3R Enables Stable Kilometer-Scale 3D Reconstruction of Long Videos

Kuaishou Tech

Aug 25, 2025 · Artificial Intelligence

How Context-as-Memory Enables Scene‑Consistent Long Video Generation

This article introduces the Context-as-Memory approach, which treats previously generated video frames as memory to achieve scene‑consistent interactive long video generation, and details a camera‑trajectory‑based memory retrieval mechanism that dramatically improves efficiency and performance over existing state‑of‑the‑art methods.

AIVideo Generationcontext memory

0 likes · 7 min read

How Context-as-Memory Enables Scene‑Consistent Long Video Generation